Chess neighborhoods, function combination, and reinforcement learning

DOI10.1007/3-540-45579-5_9MaRDI QIDQ4536684zbMATH OpenFDO

Authors Robert Levinson, Ryan Weber

Publication date 6 August 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/3-540-45579-5_9

zbMATH Keywords

computer chessexponentiated gradientgradient descentlinear regressionmulti-layer neural netsreinforcement learningtemporal difference learningvalue function approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) 2-person games (91A05) Experimental studies (91A90)

Recommendations

• Learning to play chess using temporal differences
• An acquisition of evaluation function for shogi by learning self-play
• Learning on graphs in the game of Go
• Learning long-term chess strategies from databases
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

This page was built for publication: Chess neighborhoods, function combination, and reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4536684)