This paper considers the challenge of enabling agents to learn with as little domain-specific knowledge as possible. The main contribution is HyperNEAT-GGP, a HyperNEAT-based General Game Playing approach to Atari games. By leveraging the geometric regularities present in the Atari game screen, HyperNEAT effectively evolves policies for playing two different Atari games, Asterix and Freeway. Results show that HyperNEAT-GGP outperforms existing benchmarks on these games. HyperNEAT-GGP represents a step towards the ambitious goal of creating an agent capable of learning and seamlessly transitioning between many different tasks.

PDF

To Appear In Genetic and Evolutionary Computation Conference (GECCO) 2012, 2012.

@article{hausknecht:gecco12, title={HyperNEAT-GGP: A HyperNEAT-based Atari General Game Player}, author={Matthew Hausknecht and Piyush Khandelwal and Risto Miikkulainen and Peter Stone}, booktitle={Genetic and Evolutionary Computation Conference (GECCO) 2012}, url="http://www.cs.utexas.edu/users/ai-lab/?hausknecht:gecco12", year={2012} }