A Neuroevolution Approach to General Atari Game Playing

General Game Players are learning algorithms capable of performing many different tasks without needing to be reconfigured, re-programmed, or given task-specific knowledge. The videos below show the results of general game playing algorithms applied to classic Atari 2600 video games.

Demo website

People

Matthew Hausknecht	Former Collaborator	mhauskn [at] cs utexas edu
Joel Lehman	Postdoctoral Alumni	joel [at] cs utexas edu
Risto Miikkulainen	Faculty	risto [at] cs utexas edu
Peter Stone		pstone [at] cs utexas edu

Projects

Learning Strategic Behavior in Sequential Decision Tasks

2009 - 2014

Publications

A Neuroevolution Approach to General Atari Game Playing	Matthew Hausknecht and Joel Lehman and Risto Miikkulainen and Peter Stone	IEEE Transactions on Computational Intelligence and AI in Games, 2013.	2013

Areas of Interest

General Game Playing Machine Learning Neuroevolution Reinforcement Learning