GaelVaroquaux

'''
Non-parametric computation of entropy and mutual-information

Adapted by G Varoquaux for code created by R Brette, itself
from several papers (see in the code).

This code is maintained at https://github.com/mutualinfo/mutual_info 
Please download the latest code there, to have improvements and 
bug fixes.

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