Sciweavers

Share
CIG
2006
IEEE

Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation

9 years 1 months ago
Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation
Abstract— This paper compares the use of temporal difference learning (TDL) versus co-evolutionary learning (CEL) for acquiring position evaluation functions for the game of Othello. The paper provides important insights into the strengths and weaknesses of each approach. The main findings are that for Othello, TDL learns much faster than CEL, but that properly tuned CEL can learn better playing strategies. For CEL, it is essential to use parent-child weighted averaging in order to achieve good performance. Using this method a high quality weighted piece counter was evolved, and was shown to significantly outperform a set of standard heuristic weights.
Simon M. Lucas, Thomas Philip Runarsson
Added 10 Jun 2010
Updated 10 Jun 2010
Type Conference
Year 2006
Where CIG
Authors Simon M. Lucas, Thomas Philip Runarsson
Comments (0)
books