noporpoise

#!/usr/bin/env python
# coding=utf-8
# License: Public domain (CC0)
# Isaac Turner 2016/12/05

from __future__ import print_function

import difflib
import re

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