TTSKarlsson

[printer:FLSun Super Racer]
bed_custom_model =
bed_custom_texture =
bed_shape = 129.505x11.3302,128.025x22.5742,125.57x33.6464,122.16x44.4626,117.82x54.9403,112.583x64.9999,106.49x74.5649,99.5857x83.5623,91.9238x91.9238,83.5623x99.5857,74.5649x106.49,65x112.583,54.9403x117.82,44.4626x122.16,33.6464x125.57,22.5742x128.025,11.3302x129.505,7.9602e-15x130,-11.3302x129.505,-22.5742x128.025,-33.6464x125.57,-44.4626x122.16,-54.9403x117.82,-64.9999x112.583,-74.5649x106.49,-83.5623x99.5857,-91.9238x91.9238,-99.5857x83.5623,-106.49x74.5649,-112.583x65,-117.82x54.9403,-122.16x44.4626,-125.57x33.6464,-128.025x22.5742,-129.505x11.3302,-130x1.59204e-14,-129.505x-11.3302,-128.025x-22.5742,-125.57x-33.6464,-122.16x-44.4626,-117.82x-54.9403,-112.583x-65,-106.49x-74.5649,-99.5857x-83.5623,-91.9238x-91.9238,-83.5623x-99.5857,-74.5649x-106.49,-65x-112.583,-54.9403x-117.82,-44.4626x-122.16,-33.6464x-125.57,-22.5742x-128.025,-11.3302x-129.505,-2.38806e-14x-130,11.3302x-129.505,22.5742x-128.025,33.6464x-125.57,44.4626x-122.16,54.94

machinaut

#!/usr/bin/env python

import os
import mujoco_py
import numpy as np

PATH_TO_HUMANOID_XML = os.path.expanduser('~/.mujoco/mjpro150/model/humanoid.xml')

# Load the model and make a simulator
model = mujoco_py.load_model_from_path(PATH_TO_HUMANOID_XML)

karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward