Temporal difference learning and TD-Gammon
Gerald Tesauro · Communications of the ACM · 1995
Ever since the days of Shannon's proposal for a chess-playing algorithm [12] and Samuel's checkers-learning program [10] the domain of complex board games such as Go, chess, checkers, Othello, and backgammon has been widely regarded as an ideal testing ground for exploring a variety of concepts and approaches in artificial intelligence and machine learning. Such board games offer the challenge of tremendous complexity and sophistication required to play at expert level. At the same time, the problem inputs and performance measures are clear-cut and well defined, and the game environment is readily automated in that it is easy to simulate the board, the rules of legal play, and the rules regarding when the game is over and determining the outcome.
Cited by 1,471 works. doi:10.1145/203330.203343 Open-access PDF
References
- Parallel Distributed Processing
- Multilayer feedforward networks are universal approximators
- Some Studies in Machine Learning Using the Game of Checkers
- Learning to Predict by the Methods of Temporal Differences
- Practical issues in temporal difference learning
- Neurogammon Wins Computer Olympiad
- Toward an Ideal Trainer