W2099001564
Jonathan Baxter, Andrew Tridgell, Lex Weaver · Machine Learning · 2000
In this paper we present TDLEAF(λ), a variation on the TD(λ) algorithm that enables it to be used in conjunction with game-tree search. We present some experiments in which our chess program “KnightCap” used TDLEAF(λ) to learn its evaluation function while playing on Internet chess servers. The main success we report is that KnightCap improved from a 1650 rating to a 2150 rating in just 308 games and 3 days of play. As a reference, a rating of 1650 corresponds to about level B human play (on a scale from E (1000) to A (1800)), while 2150 is human master level. We discuss some of the reasons for this success, principle among them being the use of on-line, rather than self-play. We also investigate whether TDLEAF(λ) can yield better results in the domain of backgammon, where TD(λ) has previously yielded striking success.
Cited by 130 works. doi:10.1023/a:1007634325138 Open-access PDF
Authors
References
- Reinforcement Learning: An Introduction
- Reinforcement Learning: An Introduction
- Some Studies in Machine Learning Using the Game of Checkers
- Learning to Predict by the Methods of Temporal Differences
- Introduction to Reinforcement Learning
- Neuro-dynamic Programming
- Practical issues in temporal difference learning
- Some studies in machine learning using the game of checkers
- An analysis of temporal-difference learning with function approximation
- TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play