Skip to content

Instantly share code, notes, and snippets.

View jojonki's full-sized avatar

Junki Ohmura jojonki

View GitHub Profile
@jojonki
jojonki / pg-pong.py
Last active January 6, 2017 08:47 — forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import 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