Improving heuristic mini-max search by supervised learning

Artificial Intelligence

Volumn 134, Issue 1-2, 2002, Pages 85-99

  Buro, Michael ^a  

^a NEC LABORATORIES AMERICA   (United States)

Author keywords

Evaluation function; Feature construction; GLEM; Logistello; Opening book learning; ProbCut; Selective game tree search

Indexed keywords

CORRELATION METHODS; FUNCTION EVALUATION; GAME THEORY; HEURISTIC METHODS; LEARNING SYSTEMS; TREES (MATHEMATICS);

HEURISTIC SEARCH;

ARTIFICIAL INTELLIGENCE;

EID: 0036148118     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0004-3702(01)00093-5     Document Type: Article

References (26)

1. A Bayesian approach to relevance in game playing
2. A generalized quiescence search algorithm
3. AI's greatest trends controversies
4. Statistical feature combination for the evaluation of game positions
5. ProbCut: An effective selective extension of the alpha-beta algorithm
6. The Othello match of the year Takeshi Murakami vs. Logistello
7. From simple features to sophisticated evaluation functions
8. Toward opening book learning
9. Experiments with multi-probcut a new high-quality evaluation function for Othello
10. Meiosis networks
11. Extended futility pruning
12. Adaptive null-move pruning
13. Book learning - A methodology to tune an opening book automatically
14. The development of a world-class othello program
15. Adaptive pattern-oriented chess
16. Conspiracy numbers for minmax search
17. Game tree searching by minmax approximation
18. A world-championship-level othello program
19. Some studies in machine learning using the game of checkers
20. Learning in bebe
21. Temporal difference learning TD - Gammon
22. Node splitting: A constructive algorithm for feed-forward neural networks