Singular Extensions: Adding Selectivity to Brute-Force Searching1

Anantharaman, Thomas; Campbell, Murray; Hsu, Feng-Hsiung

doi:10.3233/icg-1988-11402

Cited by 31 publications

(29 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional AI game playing programs, like Deep Thought and HiTech, use fast, deep search to identify relevant future positions and evaluate their strength (Anantharaman, Campbell, & Hsu, 1990;Berliner & Ebeling, 1989). These programs rely on special-purpose hardware, clever storage and retrieval tactics, a few well-known search heuristics, and raw computing power to search deeply and quickly.…”

Section: Related Workmentioning

confidence: 99%

Toward an ideal trainer

Epstein

1994

Mach Learn

View full text Add to dashboard Cite

Abstract. This paper demonstrates how the nature of the opposition during training affects learning to play twoperson, perfect information board games. It considers different kinds of competitive training, the impact of trainer error, appropriate metrics for post-training performance measurement, and the ways those metrics can be applied. The results suggest that teaching a program by leading it repeatedly through the same restricted paths, albeit high quality ones, is overly narrow preparation for the variations that appear in real-world experience. The results also demonstrate that variety introduced into training by random choice is unreliable preparation, and that a program that directs its own training may overlook important situations. The results argue for a broad variety of training experience with play at many levels. This variety may either be inherent in the game or introduced deliberately into the training. Lesson and practice training, a blend of expert guidance and knowledge-based, self-directed elaboration, is shown to be particularly effective for learning during competition.

show abstract

Section: Related Workmentioning

confidence: 99%

Toward an ideal trainer

Epstein

1994

Mach Learn

View full text Add to dashboard Cite

show abstract

“…" Other more ambitious selective alpha-beta schemes are described in [1,7]. However, all these schemes are deficient in that they look for certain kinds of moves on which to continue the analysis, and the definitions used by the search paradigm are not broad enough to include all useful moves.…”

Section: The History Of Selective Adversary Searchingmentioning

confidence: 99%

B* Probability Based Search1

Berliner

McConnell

1996

ICG

View full text Add to dashboard Cite

“…However, in Go, even after pruning by patterns or rules, these approaches are clearly outperformed by MCTS -all recent tournaments have been won by MCTS approaches with usually all the MCTS programs ranked better than non-MCTS programs. Interestingly, some significant improvements in chess have been achieved with "forced moves" [14]. Forced moves are moves that are almost mandatory for a player.…”

Section: Iintroductionmentioning

confidence: 99%