Bayesian learning of generalized board positions for improved move prediction in computer go

Martin Michalowski, Mark Boddy, Mike Neilsen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Computer Go presents a challenging problem for machine learning agents. With the number of possible board states estimated to be larger than the number of hydrogen atoms in the universe, learning effective policies or board evaluation functions is extremely difficult. In this paper we describe Cortigo, a system that efficiently and autonomously learns useful generalizations for large state-space classification problems such as Go. Cortigo uses a hierarchical generative model loosely related to the human visual cortex to recognize Go board positions well enough to suggest promising next moves. We begin by briefly describing and providing motivation for research in the computer Go domain. We describe Cortigo's ability to learn predictive models based on large subsets of the Go board and demonstrate how using Cortigo's learned models as additive knowledge in a state-of-the-art computer Go player (Fuego) significantly improves its playing strength.

Original languageEnglish (US)
Title of host publicationAAAI-11 / IAAI-11 - Proceedings of the 25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference
Pages815-820
Number of pages6
StatePublished - Nov 2 2011
Event25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference, AAAI-11 / IAAI-11 - San Francisco, CA, United States
Duration: Aug 7 2011Aug 11 2011

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume1

Other

Other25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference, AAAI-11 / IAAI-11
CountryUnited States
CitySan Francisco, CA
Period8/7/118/11/11

Fingerprint Dive into the research topics of 'Bayesian learning of generalized board positions for improved move prediction in computer go'. Together they form a unique fingerprint.

  • Cite this

    Michalowski, M., Boddy, M., & Neilsen, M. (2011). Bayesian learning of generalized board positions for improved move prediction in computer go. In AAAI-11 / IAAI-11 - Proceedings of the 25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference (pp. 815-820). (Proceedings of the National Conference on Artificial Intelligence; Vol. 1).