Skip to content

Instantly share code, notes, and snippets.

@ansukla
ansukla / pg-pong.py
Created Jul 5, 2017 — forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
View pg-pong.py
""" 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
View designer.html
<link rel="import" href="../paper-tabs/paper-tabs.html">
<link rel="import" href="../paper-tabs/paper-tab.html">
<link rel="import" href="../core-icons/core-icons.html">
<link rel="import" href="../paper-icon-button/paper-icon-button.html">
<link rel="import" href="../paper-button/paper-button.html">
<link rel="import" href="../paper-slider/paper-slider.html">
<polymer-element name="my-element">
<template>