KnightCap: A Chess Programm That Learns by Combining TD(lambda) with Game-Tree Search
Jonathan Baxter, Andrew Tridgell, Lex Weaver · International Conference on Machine Learning · 1998
Cited by 65 works.
Authors
References
- Some Studies in Machine Learning Using the Game of Checkers
- Learning to Predict by the Methods of Temporal Differences
- Neuro-dynamic Programming
- Practical issues in temporal difference learning
- An analysis of temporal-difference learning with function approximation
- TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
- Temporal Difference Learning of Position Evaluation in the Game of Go
- Learning to Play the Game of Chess
- Coevolution of A Backgammon Player
- Learning Piece Values Using Temporal Differences