Luke Liem LUKELIEM

A technologist and investor researching into Artificial Intelligence and how it can be used to solve humanity’s urgent problems

LUKELIEM / pg-pong.py

Created August 30, 2017 10:10 — 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 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

LUKELIEM / cem.py

Last active August 27, 2017 14:26

Cross-entropy method (provided by OpenAI Gym)

	from __future__ import print_function

	import gym
	from gym import wrappers
	import logging
	import numpy as np
	try:
	import cPickle as pickle
	except ImportError:
	import pickle