rmihir96

#!/usr/bin/env python
# coding: utf-8

# In[1]:



from fastai.vision import *
from fastai.metrics import *
import glob

rmihir96

""" 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