A Neuroevolution Approach to General Atari Game Playing (2013)
Author: Matthew Hausknecht

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 Formerly affiliated 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 Faculty pstone [at] cs utexas edu
Projects
Learning Strategic Behavior in Sequential Decision Tasks 2009 - 2014
Publications
A Neuroevolution Approach to General Atari Game Playing 2013
Matthew Hausknecht, Joel Lehman, Risto Miikkulainen, and Peter Stone, IEEE Transactions on Computational Intelligence and AI in Games (2013).
Related Areas
General Game Playing Machine Learning Neuroevolution Reinforcement Learning
Labs
Learning Agents Neural Networks