HyperNEAT-GGP: a hyperNEAT-based atari general game player

Authors:
Matthew Hausknecht;Piyush Khandelwal;Risto Miikkulainen;Peter Stone
Affiliations:
University of Texas at Austin, Austin, TX, USA;University of Texas at Austin, Austin, TX, USA;University of Texas at Austin, Austin, USA;University of Texas at Austin, Austin, USA
Venue:
Proceedings of the 14th annual conference on Genetic and evolutionary computation
Year:
2012

Citing 12
Cited 1

TD-Gammon, a self-teaching backgammon program, achieves master-level play

Neural Computation
Deep Blue

Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
Evolving neural networks through augmenting topologies

Evolutionary Computation
Scaling Reinforcement Learning toward RoboCup Soccer

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Generative encoding for multiagent learning

Proceedings of the 10th annual conference on Genetic and evolutionary computation
An object-oriented representation for efficient reinforcement learning

Proceedings of the 25th international conference on Machine learning
Ms Pac-Man competition

ACM SIGEVOlution
A case study on the critical role of geometric regularity in machine learning

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Evolving coordinated quadruped gaits with the HyperNEAT generative encoding

CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Backpropagation without human supervision for visual control in quake II

CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Evolving Static Representations for Task Transfer

The Journal of Machine Learning Research
Reinforcement Learning: An Introduction

IEEE Transactions on Neural Networks

The arcade learning environment: an evaluation platform for general agents

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.