Created
September 1, 2018 10:47
-
-
Save sappelt/4bcb5701129625c92fa6576578656494 to your computer and use it in GitHub Desktop.
FrozenLake with q-tables and refactored to deep q-learning
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "code", | |
| "execution_count": 1, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "import numpy as np\n", | |
| "import gym\n", | |
| "\n", | |
| "import random" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 2, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "env = gym.make(\"FrozenLake-v0\")" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 3, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "4\n", | |
| "16\n", | |
| "\n", | |
| "\u001b[41mS\u001b[0mFFF\n", | |
| "FHFH\n", | |
| "FFFH\n", | |
| "HFFG\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "action_size = env.action_space.n\n", | |
| "state_size = env.observation_space.n\n", | |
| "\n", | |
| "# Actions are left, up, right, down\n", | |
| "print(action_size)\n", | |
| "# States are the 16 fields\n", | |
| "print(state_size)\n", | |
| "env.render()" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 4, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "[[0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]\n", | |
| " [0. 0. 0. 0.]]\n" | |
| ] | |
| } | |
| ], | |
| "source": [ | |
| "# q table where rows=states, columns=actions\n", | |
| "qtable = np.zeros((state_size, action_size))\n", | |
| "print(qtable)" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 5, | |
| "metadata": {}, | |
| "outputs": [], | |
| "source": [ | |
| "total_episodes = 15000 # Total episodes\n", | |
| "learning_rate = 0.8 # Learning rate\n", | |
| "max_steps = 99 # Max steps per episode\n", | |
| "gamma = 0.95 # Discounting rate\n", | |
| "\n", | |
| "# Exploration parameters\n", | |
| "epsilon = 1.0 # Exploration rate\n", | |
| "max_epsilon = 1.0 # Exploration probability at start\n", | |
| "min_epsilon = 0.01 # Minimum exploration probability \n", | |
| "decay_rate = 0.005 # Exponential decay rate for exploration prob" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "execution_count": 6, | |
| "metadata": {}, | |
| "outputs": [ | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n" | |
| ] | |
| }, | |
| { | |
| "name": "stdout", | |
| "output_type": "stream", | |
| "text": [ | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 1.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", | |
| "Reward: 0.0\n", |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment