Loading [MathJax]/extensions/MathMenu.js
Coevolutionary Temporal Difference Learning for Othello | IEEE Conference Publication | IEEE Xplore

Coevolutionary Temporal Difference Learning for Othello


Abstract:

This paper presents Coevolutionary Temporal Difference Learning (CTDL), a novel way of hybridizing co-evolutionary search with reinforcement learning that works by interl...Show More

Abstract:

This paper presents Coevolutionary Temporal Difference Learning (CTDL), a novel way of hybridizing co-evolutionary search with reinforcement learning that works by interlacing one-population competitive coevolution with temporal difference learning. The coevolutionary part of the algorithm provides for exploration of the solution space, while the temporal difference learning performs its exploitation by local search. We apply CTDL to the board game of Othello, using weighted piece counter for representing players' strategies. The results of an extensive computational experiment demonstrate CTDL's superiority when compared to coevolution and reinforcement learning alone, particularly when coevolution maintains an archive to provide historical progress. The paper investigates the role of the relative intensity of coevolutionary search and temporal difference search, which turns out to be an essential parameter. The formulation of CTDL leads also to the introduction of Lamarckian form of coevolution, which we discuss in detail.
Date of Conference: 07-10 September 2009
Date Added to IEEE Xplore: 13 October 2009
ISBN Information:

ISSN Information:

Conference Location: Milan, Italy

References

References is not available for this document.