Sciweavers

Share
CG
2006
Springer

Feature Construction for Reinforcement Learning in Hearts

8 years 9 months ago
Feature Construction for Reinforcement Learning in Hearts
Temporal difference (TD) learning has been used to learn strong evaluation functions in a variety of two-player games. TD-gammon illustrated how the combination of game tree search and learning methods can achieve grand-master level play in backgammon. In this work, we develop a player for the game of hearts, a 4-player game, based on stochastic linear regression and TD learning. Using a small set of basic game features we exhaustively combined features into a more expressive representation of the game state. We report initial results on learning with various combinations of features and training under self-play and against search-based players. Our simple learner was able to beat one of the best search-based hearts programs.
Nathan R. Sturtevant, Adam M. White
Added 13 Oct 2010
Updated 13 Oct 2010
Type Conference
Year 2006
Where CG
Authors Nathan R. Sturtevant, Adam M. White
Comments (0)
books