Changes

'''Opponent Model Search''' incorporates asymmetric search and [[Asymmetric Evaluation|asymmetric evaluation]] techniques considering the peculiarities of an opponent, which requires explicit [[Knowledge|knowledge]] or assumption, and includes a model on how the opponent evaluates positions. Naive approaches in computer chess tournaments are [[Opening Book|opening book]] preparation and [[Contempt Factor|contempt]]. Some chess programs, notably [[Psion]] <ref>[[Kaare Danielsen]] ('''1987'''). ''The 7th World Microcomputer Chess Championship, Rome, Italy, September 14-20, 1987''. [[ICGA Journal#10_3|ICCA Journal, Vol. 10, No. 3]] » [[WMCCC 1987]]</ref> , its successor [[Chess Genius]] <ref>[http://groups.google.com/group/rec.games.chess.computer/browse_frm/thread/b456400a43207b02 Genius' asymmetric-search by example: TRY yourself] by [[Thorsten Czub]], [[Computer Chess Forums|rgcc]], December 30, 1997</ref> , and [[KnightCap]] <ref>[https://groups.google.com/group/rec.games.chess.computer/msg/f9bfe5d4457a19ad asymmetry] by [[Andrew Tridgell]], [[Computer Chess Forums|rgcc]], August 12, 1997</ref> , apply [[Asymmetric evaluation|asymmetric evaluation]] and search, for instance to [[Extensions|extend]] when the own side is in trouble but not the opponent. Other programs, like [[Crafty]], can be adapted asymmetric for playing human chess players, specially [[Anti-Computerchess|anti-computerchess]] specialists, for instance to reduce the program's tendency to trade material and to avoid blocked positions with a high [[Pawn Rams (Bitboards)|rammed pawn]] versus [[Pawn Levers (Bitboards)|lever]] ratio. [[Ed Schroder|Ed Schröder]] proposed to reward own [[Hanging Piece|hanging pieces]] to encourage complicated, [[Tactics|tactical]] play versus humans, and to keep opponents under time pressure in playing immediate [[Pondering|ponder hits]] <ref>[http://www.open-chess.org/viewtopic.php?f=5&t=2546&start=1 Re: Anti Coward Mode] by [[Ed Schroder|Rebel]], [[Computer Chess Forums|OpenChess Forum]], December 22, 2013</ref> . Programs may [[Automated Tuning|tune]] and [[Learning|learn]] feature vectors and their respective weights to maximize result scores against certain opponents as well.

Opponent Model search was further investigated by various game researchers, such as [[Mathematician#DCarmel|David Carmel]], [[Shaul Markovitch]], [[Xinbo Gao]], [[Hiroyuki Iida]], [[Jos Uiterwijk]], [[Jaap van den Herik]], [[Bob Herschberg]], [[Jeroen Donkers]], [[Pieter Spronck]] and [[Sander Bakkes]].

Carmel and Markovitch introduced '''M'''* <ref>[[Mathematician#DCarmel|David Carmel]], [[Shaul Markovitch]] ('''19931994'''). ''Learning [https://www.semanticscholar.org/paper/The-M*-Algorithm%3A-Incorporating-Opponent-Models of -Carmel-Markovitch/bd788272c81951dc44fa7944e0f72451ced14129 The M* Algorithm: Incorporating Opponent's Strategy in Game PlayingModels into Adversary Search]''. [[AAAI]] ProceedingsCIS Report #9402, [http://citeseerxwww.istcs.psutechnion.eduac.il/~shaulm/papers/viewdocpdf/summary?doi=10Carmel-Markovitch-CIS9402.1.1.55.6488 CiteSeerXpdf pdf]</ref> , a generalization of [[Minimax|minimax]] that uses an arbitrary opponent model to simulate the opponent’s search, and further proved a sufficient condition for pruning and present the '''αβ'''* algorithm which returns the M* value of a tree while searching only necessary branches <ref>[[Mathematician#DCarmel|David Carmel]], [[Shaul Markovitch]] ('''1996'''). ''Incorporating Opponent Models into Adversary Search''. [[Conferences#AAAI-96|AAAI1996]] 1996 Proceedings, [http://www.aaaics.technion.ac.orgil/Papers~shaulm/AAAIpapers/1996pdf/AAAI96Carmel-Markovitch-018aaai1996.pdf pdf]</ref> . Gao et al. researched on a generalization of opponent model search, called '''(D, d)-OM''' search, where '''D''' stands for the [[Depth|depth]] of [[Search|search]] by the player and '''d''' for the opponent’s depth of search <ref>[[Xinbo Gao]], [[Hiroyuki Iida]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''1998'''). ''[http://link.springer.com/chapter/10.1007/3-540-48957-6_5 A Speculative Strategy]''. [[CG 1998]]</ref> . The '''Probabilistic''' Opponent-Model Search ('''PrOM''') for several game domains was developed by Donkers, Uiterwijk and Van den Herik, published in 2000 <ref>[[Jeroen Donkers]], [[Jos Uiterwijk]], [[Jaap van den Herik]] ('''2000'''). ''Investigating Probabilistic Opponent-Model Search''. JCIS 2000, [http://www.fdg.unimaas.nl/educ/donkers/pubs/..%5Cpdf%5Cbnaic00.pdf pdf] (extended abstract)</ref> . It uses an extended model that includes uncertainty of the opponent.

* [[Mathematician#DCarmel|David Carmel]], [[Shaul Markovitch]] ('''1993'''). ''[https://aaai.org/Library/Symposia/Fall/1993/fs93-02-019.php Learning Models of Opponent's Strategy in Game Playing]''. [[Conferences#AAAI-93|AAAI 1993]] Proceedings, FS-93-02, [httphttps://citeseerxwww.istaaai.psu.eduorg/Papers/Symposia/Fall/1993/viewdocFS-93-02/summary?doi=10.1.1.55FS93-02-019.6488 CiteSeerXpdf pdf]

* [[Mathematician#DCarmel|David Carmel]], [[Shaul Markovitch]] ('''1994'''). ''[https://www.semanticscholar.org/paper/The-M*-Algorithm%3A-Incorporating-Opponent-Models-Carmel-Markovitch/bd788272c81951dc44fa7944e0f72451ced14129 The M* Algorithm: Incorporating Opponent Models into Adversary Search]''. CIS Report #9402, [http://www.cs.technion.ac.il/~shaulm/papers/pdf/Carmel-Markovitch-CIS9402.pdf pdf] <ref>[http://www.talkchess.com/forum/viewtopic.php?t=54865&start=27 Re: Different eval for white/black] by [[Ronald de Man]], [[CCC]], January 08, 2015</ref>

* [[Mathematician#DCarmel|David Carmel]], [[Shaul Markovitch]] ('''1996'''). ''Incorporating Opponent Models into Adversary Search''. [[Conferences#AAAI-96|AAAI 1996]] 1996 Proceedings, [http://www.aaaics.orgtechnion.ac.il/Papers~shaulm/AAAIpapers/1996pdf/AAAI96Carmel-Markovitch-018aaai1996.pdf pdf]

* [[Jaap van den Herik]], [[Jeroen Donkers]], [[Pieter Spronck]] ('''2005'''). ''Opponent Modelling and Commercial Games''. (Keynote paper). CIG’05, [httphttps://www.fdgscimagojr.unimaas.nl/educ/donkers/pubscom/journalsearch..%5Cpdf%5Cherikcig2005.pdf pdfphp?q=20000195030&tip=sid&clean=0 CIG’05].

* [http://www.talkchess.com/forum/viewtopic.php?t=54865 Different eval for white/black] by [[Matthew Lai]], [[CCC]], January 05, 2015 » [[Asymmetric evaluationEvaluation]]