DamienAllonsius

""" 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

DamienAllonsius

#!/usr/bin/env python3
#-*- coding: utf-8 -*-

# Very simple tetris implementation
#
# Control keys:
#       Down - Drop stone faster
# Left/Right - Move stone
#         Up - Rotate Stone clockwise
#     Escape - Quit game