Computer Go Bibliography

[AW01]
Myriam Abramson and Harry Wechsler. Competitive reinforcement learning for combinatorial problems. In INNS-IEEE International Joint Conference on Neural Networks (IJCNN 2001), 2001. [ http://mysite.verizon.net/mabramso/research/ijcnn2001.pdf ]
Keywords: Learning Vector Quantization, SLVQ, SARSA
[AH03b]
Myriam Abramson and Wechsler Harry. Tabu search exploration for on-policy reinforcement learning. In International Neural Network Conference, Portland, OR, 2003. [ http://mysite.verizon.net/mabramso/research/tabuijcnn03.pdf ]
Keywords: Reinforcement learning, tabu search, Sarsa Learning Vector Quantization
[AH03a]
Myriam Abramson and Wechsler Harry. A distributed reinforcement learning approach to pattern inference in Go. In International Conference on Machine Learning Applications, Los Angeles, CA, 2003. [ http://mysite.verizon.net/mabramso/research/icmla2003.pdf ]
Keywords: reinforcement learning, LVQ
[Abr03]
Myriam Abramson. Learning Coordination Strategies. PhD thesis, George Mason University, 2003. [ http://mysite.verizon.net/mabramso/research/Dissert.pdf ]
Keywords: Reinforcement learning, tabu search, Sarsa Learning Vector Quantization
[DKR02]
Brian Drabble, Jana Koehler, and Ioannis Refanidis, editors. Sixth International Conference on AI Planning & Scheduling, Workshop Notes, Planning and Scheduling with Multiple Criteria. Laboratory for Analysis and Architecture of Systems, Toulouse, 2002. [ http://www.laas.fr/aips/ws-tu1.pdf ]
[All94]
Victor L. Allis. Searching for Solutions in Games and Artificial Intelligence. PhD thesis, University of Limburg, 1994. [ http://fragrieu.free.fr/SearchingForSolutions.pdf ]
Keywords: go, AI, pn-search, db-search, proof-number, awari, backgammon, bridge, chess, Chinese chess, checkers, connect-four, draughts, go-moku, nine men's morris, othello, qubic, renju, scrabble
[Alt00]
Ingo Althöfer. 3-hirn - new ways in Go with computers, 2000. Notes on seminar, given at the European Go Congress, Berlin, 10 August, 2000. [ http://www.mathematik.uni-jena.de/www/fakultaet/iam/personen/StrausTalke.html ]
Keywords: 3-Hirn, Dreihirn
[AYTT07]
Nobuo Araki, Kazuhiro Yoshida, Yoshimasa Tsuruoka, and Jun'ichi Tsujii. Move prediction in Go with the maximum entropy method. In 2007 IEEE Symposium on Computational Intelligence and Games, 2007. [ http://www-tsujii.is.s.u-tokyo.ac.jp/~ark/publications/CIG2007.pdf ]
Keywords: move prediction, pattern learning, maximum entropy method, re-ranking
[Ben76]
David B. Benson. Life in the game of Go. Information Sciences, 10:17-29, 1976. [ http://www.cs.ualberta.ca/~games/go/seminar/2002/020717/benson.pdf ]
Keywords: life and death, algorithm, static
[Ber96]
Elwyn Berlekamp. The Economist's View of Combinatorial Games, pages 365-405. Cambridge University Press, 1996. [ http://www.msri.org/publications/books/Book29/files/ber.pdf ]
Keywords: go, combinatorial game theory, thermograph, temperature
[BK96]
Elwyn Berlekamp and Yonghoan Kim. Where Is the “Thousand-Dollar Ko”?, pages 203-226. Cambridge University Press, 1996. [ http://www.msri.org/publications/books/Book29/files/kim.pdf ]
Keywords: go, combinatorial game, endgame, ko
[Ber01]
Elwyn Berlekamp. Idempotents Among Partisan Games, pages 1-23. Cambridge University Press, 2001. [ http://math.berkeley.edu/~berlek/papers/idem.ps ]
Keywords: Idempotents, Combinatorial game theory
[Bew98]
Joerg Bewersdorff. Go und Mathematik, 1998. In German. [ http://www.galois-theorie.de/pdf/go.pdf ]
Keywords: go, mathematics, combinatorial game theory
[BV92]
Bruno Bouzy and Bernard Victorri. Go et intelligence artificielle. Revue de l'AFIA, 10, 1992. In French. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/AFIA92.article.pdf ]
[Bou95c]
Bruno Bouzy. Modelisation cognitive du joueur de Go. PhD thesis, Universite Paris, 1995. In French. [ ftp://ftp-igs.joyjoy.net/Go/computer/bbthese.ps.Z ]
Keywords: Indigo
[Bou95b]
Bruno Bouzy. Les ensemble flous au jeu de Go. In Actes des Recontres francophones sur la Ligique Floue et ses Applications, LFA 1995, 1995. In French. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/flou.article.pdf ]
[Bou95a]
Bruno Bouzy. The INDIGO program. In Proceedings of the 2nd Game Programming Workshop in Japan, Kanagawa 1995, 1995. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/indigo.article.pdf ]
Keywords: INDIGO
[Bou95d]
Bruno Bouzy. Towards spatial reasoning about “natural” objects. Technical report, LIAFA - Université Denis Diderot, 1995. [ http://www.liafa.jussieu.fr/web9/rapportrech/rapport/1995/tospare.pdf ]
Keywords: Spatial reasoning, Objects, Natural versus Artificial, Relationships, Fractal dimension
[Bou96b]
Bruno Bouzy. Spatial reasoning in the game of Go, 1996. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/SRGo.article.pdf ]
Keywords: spatial reasoning, objects, relationships
[BC96]
Bruno Bouzy and Tristan Cazenave. Shared concepts between complex domains and the game of Go, 1996. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/UES96.article.pdf ]
Keywords: economy, social sciences, war simulation, linguistic, biology, earth sciences
[Bou96c]
Bruno Bouzy. There are no winning moves except the last, 1996. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/incertitude.article.pdf ]
Keywords: INDIGO
[Bou96a]
Bruno Bouzy. Incremental updating of objects in INDIGO, 1996. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/incremental.article.pdf ]
Keywords: incremental
[Bou99]
Bruno Bouzy. Complex games in practice. In Fifth Game Programming Workshop in Japan, 1999. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/GPW99.pdf ]
Keywords: Group strength, Monocolor Tree Search, Killing and Living Moves Numbers
[Bou01a]
Bruno Bouzy. Go patterns generated by retrograde analysis. In Computer Olympiads, Maastricht, 2001. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/RAGO.pdf ]
Keywords: Retrograde analysis
[BC01]
Bruno Bouzy and Tristan Cazenave. Computer Go: an AI oriented survey, 2001. Preprint for article in AI Journal. To be published. [ http://www.math-info.univ-paris5.fr/~bouzy/CG-AISurvey.ps.gz ]
Keywords: survey
[Bou01b]
Bruno Bouzy. Le role des concepts spatiaux dans la programmation du jeu de go. Revue d'Intelligence Artificielle, 2001. In French. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/RoleConceptsSpatiauxPdG.pdf ]
[Bou02]
Bruno Bouzy. A small Go board study of metric and dimensional evaluation functions. In 3rd Computer and Games Conference, Edmonton, 2002. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/CG2002-Bouzy.pdf ]
Keywords: very-little-knowledge evaluation function, distance, dimension
[Bou03c]
Bruno Bouzy. The move decision strategy of Indigo. ICGA Journal, 26(1), 2003. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/MyBouzy-ICGAJournal.pdf ]
Keywords: Quick & slow evaluation, strategic evaluation, urgent move selection, single-agent & two-agent search
[Bou03b]
Bruno Bouzy. Mathematical morphology applied to computer go. IJPRAI, 17(2), 2003. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/MyBouzy-IJPRAI.pdf ]
Keywords: Mathematical morphologu, territory, dilation, erosion, closing
[BH03]
Bruno Bouzy and Bernard Helmstetter. Monte Carlo Go developments. In Ernst A. Heinz H. Jaap van den Herik, Hiroyuki Iida, editor, Advances in Computer Games conference (ACG-10), Graz 2003, pages 159-174. Kluwer, 2003. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/bouzy-helmstetter.pdf ]
Keywords: Monte-Carlo approach, heuristics
[Bou03a]
Bruno Bouzy. Associating domain-dependent knowledge and Monte Carlo approaches within a Go program. In Joint Conference on Information Sciences, 2003. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/Bouzy-JCIS03.pdf ]
Keywords: Monte Carlo, Indigo, Olga
[Bou04b]
Bruno Bouzy. Associating shallow and selective global tree search with Monte Carlo for 9x9 Go. In 4rd Computer and Games Conference, Ramat-Gan, 2004. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/cg04-bouzy.pdf ]
Keywords: Min-max, progressive pruning, Indigo
[Bou04a]
Bruno Bouzy. The 4th Computers and Games conference. ICGJ, 27(3), 2004. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/CG04-report.pdf ]
Keywords: 9th Computer Olympiad
[BC05b]
Bruno Bouzy and Guillaume Chaslot. Extraction bayesienne et integration de patterns representes suivant les k plus proches voisins pour le go 19x19. In Actes de la conference EGC05, 2005. In French. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/bouzy-chaslot-egc05.pdf ]
[Bou05a]
Bruno Bouzy. Associating domain-dependent knowledge and Monte Carlo approaches within a Go program. Information Sciences, 2005. To appear. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/Bouzy-InformationSciences.pdf ]
Keywords: Monte Carlo, domain-dependent knowledge, Indigo
[BC05a]
Bruno Bouzy and Guillaume Chaslot. Bayesian generation and integration of k-nearest-neighbor patterns for 19x19 Go. In G. Kendall and Simon Lucas, editors, IEEE 2005 Symposium on Computational Intelligence in Games, Colchester, UK, pages 176-181, 2005. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/bouzy-chaslot-cig05.pdf ]
Keywords: K-nearest-neighbor, pattern database
[Bou05b]
Bruno Bouzy. History and territory heuristics for Monte-Carlo Go. In Joint Conference on Information Sciences, Salt Lake City, Heuristic Search and Computer Game Playing Session, 2005. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/bouzy-jcis05.pdf ]
Keywords: territory heuristic, history heuristic, Indigo
[Bou05c]
Bruno Bouzy. Move pruning techniques for Monte-Carlo Go. In 11th Advances in Computer Game conference, Taipei, 2005. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/bouzy-acg11.pdf ]
Keywords: Monte-Carlo Go, progressive pruning, Miai pruning, set pruning
[BC06]
Bruno Bouzy and Guillaume Chaslot. Monte-Carlo Go reinforcement learning experiments. In G. Kendall and S. Louis, editors, IEEE 2006 Symposium on Computational Intelligence in Games, Reno, USA, 2006. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/bouzy-chaslot-cig06.pdf ]
Keywords: Monte-Carlo Go, reinforcement learning, Indigo
[CWvdH+07]
Guillaume Chaslot, Mark Winands, H. Jaap van den Herik, Jos Uiterwijk, and Bruno Bouzy. Progressive strategies for Monte-Carlo tree search. In Joint Conference on Information Sciences, Salt Lake City 2007, Heuristic Search and Computer Game Playing Session, 2007. [ http://www.math-info.univ-paris5.fr/~bouzy/publications/CWHUB-pMCTS-2007.pdf ]
Keywords: Monte-Carlo, progressive bias, progressive unpruning, Mango
[Br3]
Bernd Brügmann. Monte Carlo Go, 1993. [ ftp://ftp.cgl.ucsf.edu/pub/pett/go/ladder/mcgo.ps ]
Keywords: go, statistical, simulated annealing
[BW95c]
Jay Burmeister and Janet Wiles. An introduction to the computer Go field and associated Internet resources. Technical Report CS-TR-339, Department of Computer Science, University of Queensland, 1995. [ http://www.itee.uq.edu.au/~janetw/Computer Go/CS-TR-339.html ]
Keywords: Internet, introduction, overview
[BWP95a]
Jay Burmeister, Janet Wiles, and Helen Purchase. The integration of cognitive knowledge into perceptual representations in computer Go. In 2nd Game Programming Workshop in Japan, Kanagawa, 1995. [ http://www.itee.uq.edu.au/~janetw/Computer Go/c-p.integration.pdf ]
Keywords: perception, cognition, knowledge
[BW95a]
Jay Burmeister and Janet Wiles. Accessing Go and computer Go resources on the Internet. In 2nd Game Programming Workshop in Japan, Kanagawa, 1995. [ http://www.itee.uq.edu.au/~janetw/Computer Go/comp-go.internet.pdf ]
Keywords: Internet
[BW95b]
Jay Burmeister and Janet Wiles. The challenge of Go as a domain for AI research: A comparision between Go and chess. In 3rd Australian and New Zealand Conference on Intelligent Information Systems, Perth, 1995. [ http://www.itee.uq.edu.au/~janetw/Computer Go/go-vs-chess.pdf ]
Keywords: chess
[BWP95b]
Jay Burmeister, Janet Wiles, and Helen Purchase. On relating local and global factors: A case study from the game of Go. In 3rd Australian and New Zealand Conference on Intelligent Information Systems, Perth, 1995. [ http://www.itee.uq.edu.au/~janetw/Computer Go/l-g.factors.pdf ]
Keywords: top-down, bottom-up, local, global, integration
[BW96]
Jay Burmeister and Janet Wiles. The use of inferential information in remembering Go positions. In Third Game Programming Workshop, Kanagawa, Japan, September 1996. [ http://www.itee.uq.edu.au/~janetw/Computer Go/inf.info.pdf ]
Keywords: memory, inference, human
[BW97]
Jay Burmeister and Janet Wiles. AI techniques used in computer Go. In Fourth Conference of the Australasian Cognitive Science Society, Newcastle, 1997. [ http://www.itee.uq.edu.au/~janetw/Computer Go/comp-go.AI.pdf ]
Keywords: AI
[BSYW97]
Jay Burmeister, Yasuki Saito, Atsushi Yoshikawa, and Janet Wiles. Memory performance of master Go players. In IJCAI workshop Using Games as an Experimental Testbed for AI Research, Nagoya, August 1997. [ http://www.itee.uq.edu.au/~janetw/Computer Go/go-master.pdf ]
Keywords: memory, human
[Bur01]
Jay Burmeister. Studies in Human and Computer Go: Assessing the Game of Go as a Research Domain for Cognitive Science. PhD thesis, The University of Queensland, Australia, October 2001. [ http://www.itee.uq.edu.au/~janetw/Computer Go/PhD_thesis.pdf ]
Keywords: Cognitive psychology, learning, Many Faces of Go, Go4++, sequential pennies-guessing task, sequential construction task
[CW01]
Xindi Cai and D.C. II Wunsch. A parallel computer-Go player, using HDP method. In IJCNN '01. International Joint Conference on Neural Networks., volume 4, pages 2373-2375, 2001. [ http://www.ece.umr.edu/acil/Publications/CONFERENCE/A parallel computer-Go.pdf ]
[Cal97]
Thomas Caldwell. Can computers 'Go' beyond chess? Computing Japan Magazin, 9, 1997. [ http://www.cjmag.co.jp/magazine/issues/1997/sept97/0997wchess.html ]
Keywords: comparison, chess, Bozulich, Nihon Ki-in
[RC01]
David Al-Dabass Richard Cant, Julian Churchill. Using hard and soft artificial intelligence algorithms to simulate human Go playing techniques. International Journal of Simulation Systems, Science & Technology, 2(1):31-49, June 2001. [ http://ducati.doc.ntu.ac.uk/uksim/journal/Vol-2/No-1/RichardCant/Cant.pdf ]
Keywords: Neural Networks, Alpha beta search, NeuralGo, Many Faces of Go
[CCAD02]
Richard Cant, Julian Churchill, and David Al-Dabass. A hybrid artificial intelligence approach with application to games. In IEEE02, 2002. [ http://ducati.doc.ntu.ac.uk/uksim/dad/webpagepapers/IEEE02/CantChrchill-Hawaii.pdf ]
Keywords: Neural Networks, Alpha beta search
[Caz94]
Tristan Cazenave. Systeme apprenant a jouer au Go. Deuxieme Rencontres des jeunes chercheurs en IA, 1994. In French. [ http://www.ai.univ-paris8.fr/~cazenave/rjcia.pdf ]
Keywords: learning
[Caz95]
Tristan Cazenave. Management of uncertainty in combinatorial game theory. Technical Report 95-10, Laforia, Paris, 1995. [ http://www.ai.univ-paris8.fr/~cazenave/cgtmu.ps.gz ]
Keywords: uncertainty, risk, combinatorial game theory
[Caz96a]
Tristan Cazenave. Automatic acquisition of tactical Go rules. In 3rd Game Programming Workshop in Japan, Hakone, 1996. [ http://www.ai.univ-paris8.fr/~cazenave/gpw96.pdf ]
Keywords: machine learning, meta knowledge, knowledge acquisition, game theory, Gogol
[Caz96b]
Tristan Cazenave. Automatic ordering of predicates by metarules. International Workshop “META'96”, Bonn 1996, 1996. [ http://www.ai.univ-paris8.fr/~cazenave/meta96.pdf ]
Keywords: meta programming, meta reasoning, first order logic, machine learning
[Caz96d]
Tristan Cazenave. Self fuzzy learning. International Workshop “LPSC'96”, 1996. [ http://www.ai.univ-paris8.fr/~cazenave/fuzzy.pdf ]
Keywords: explanation based learning, fuzzy logic, strategy
[Caz96c]
Tristan Cazenave. Learning to forecast by explaining the consequences of actions. International Workshop “MALFO'96”, 1996. [ http://www.ai.univ-paris8.fr/~cazenave/malfo96.pdf ]
Keywords: explanation based learning, metaknowledge, combinatorial game theory, Gogol
[CN96]
Tristan Cazenave and Jean-Marc Nigro. Constraint based explanations in games. International Conference “IPMU'96”, 1996. [ http://www.ai.univ-paris8.fr/~cazenave/ipmu96.pdf ]
Keywords: explanation based learning
[Caz97b]
Tristan Cazenave. Système d'Apprentissage Par Auto-Observation. Application au jeu de Go. PhD thesis, Universite Paris, 1997. In French. [ http://www.ai.univ-paris8.fr/~cazenave/these.pdf ]
Keywords: machine learning, self observation, combinatorial game theory, generalization, explanation, compilation, management
[Caz97a]
Tristan Cazenave. Gogol (an analytical learning program). FOST cup, IJCAI'97, 1997. [ http://www.ai.univ-paris8.fr/~cazenave/fost97.pdf ]
Keywords: Gogol
[CM97]
Tristan Cazenave and Régis Moneret. Development and evaluation of strategic plans. In Game Programming Workshop in Japan'97, Hakone, 1997. [ http://www.ai.univ-paris8.fr/~cazenave/gpw97.pdf ]
Keywords: evaluation, AND/OR search, probability estimation, goals
[Caz98a]
Tristan Cazenave. Controlled partial evaluation of declarative logic programs. In ACM Computing Surveys 1998, Symposium on Partial Evaluation, 1998. [ http://www.ai.univ-paris8.fr/~cazenave/sope.pdf ]
Keywords: tactical theorem prover, partial dediction, partial evaluation,
[Caz98d]
Tristan Cazenave. Metaprogramming forced moves. In ECAI-98, 1998. [ http://www.ai.univ-paris8.fr/~cazenave/ecai98.pdf ]
Keywords: forced moves, metaprogramming
[Caz98e]
Tristan Cazenave. Speedup mechanisms for large learning systems. In IPMU 98, Paris, 1998. [ http://www.ai.univ-paris8.fr/~cazenave/ipmu98.pdf ]
Keywords: knowledge representation, generality, efficiency, speedup rules
[Caz98b]
Tristan Cazenave. Integration of different reasoning modes in a Go playing and learning system. In AAAI Spring Symposium on Multimodal Reasoning, Stanford, 1998. [ http://www.ai.univ-paris8.fr/~cazenave/multimodal98.pdf ]
Keywords: rule-based reasoning, case-based reasoning, constrained-based reasoning, tactics, strategy, planning
[Caz98f]
Tristan Cazenave. Strategic evaluation in complex domains. FLAIRS 98, 1998. [ http://www.ai.univ-paris8.fr/~cazenave/Flairs98.pdf ]
Keywords: evaluation
[Caz98c]
Tristan Cazenave. Machine self-consciousness more efficient than human self-consciousness. European Meeting on Cybernetics and Systems Research, 1998. [ http://www.ai.univ-paris8.fr/~cazenave/emcsr98.pdf ]
Keywords: consciousness, introspection, cognitive science
[Caz99b]
Tristan Cazenave. Generation of patterns with external conditions for the game of Go. In Advances in Computer Games Conference, Paderborn, 1999. [ http://www.ai.univ-paris8.fr/~cazenave/acg9-final.pdf ]
Keywords: pattern databases, external conditions
[Caz99a]
Tristan Cazenave. Generating search knowledge in a class of games, 1999. Submitted paper. [ http://www.ai.univ-paris8.fr/~cazenave/cazenave_heuristic.ps.gz ]
Keywords: Introspect, search knowledge, meta-knowledge
[Caz00]
Tristan Cazenave. Abstract proof search, 2000. Submitted paper. [ http://www.ai.univ-paris8.fr/~cazenave/APS-final.pdf ]
Keywords: Computer Go, Search, Theorem Proving, Capture Game
[Caz01c]
Tristan Cazenave. A problem library for computer Go. IJCAI-01 Workshop on Empirical AI, 2001. [ http://www.ai.univ-paris8.fr/~cazenave/GoTest-IJCAI01.pdf ]
Keywords: problem collections, evaluation of programs
[Caz01d]
Tristan Cazenave. Theorem proving in the game of Go. In First International Conference on the Scientific Study of Go, Seoul, 2001. [ http://www.ai.univ-paris8.fr/~cazenave/TheoremProvingInGo.pdf ]
Keywords: theorem proving
[Caz01b]
Tristan Cazenave. Iterative widening. In IJCAI-01, 2001. [ http://www.ai.univ-paris8.fr/~cazenave/iw00.pdf ]
Keywords: abstract proof search
[Caz02d]
Tristan Cazenave. La recherche abstraite graduelle de preuve. RFIA-02, 2002. In French. [ http://www.ai.univ-paris8.fr/~cazenave/AGPS-RFIA.pdf ]
Keywords: AtariGo, Capture Go, AND/OR tree search, problem solving, Hex, Gomoku
[Caz01a]
Tristan Cazenave. Gradual abstract proof search. ICGA, 25(1):3-15, 2001. [ http://www.ai.univ-paris8.fr/~cazenave/gaps.pdf ]
Keywords: Gradual Abstract Proof Search, GAPS, Atari-Go, Phutball
[Caz02c]
Tristan Cazenave. A generalized threats search algorithm. In Computers and Games 2002, Edmonton, Canada, 2002. [ http://www.ai.univ-paris8.fr/~cazenave/gta.pdf ]
Keywords: Generalized Threats Search, GTS, Atari-Go
[Caz02a]
Tristan Cazenave. Admissible moves in two-player games. In SARA 2002, LNCS 2371, pages 52-63, 2002. [ http://www.ai.univ-paris8.fr/~cazenave/admissibleSARA2002.pdf ]
Keywords: admissible heuristics, Gradual Abstract Proof Search, AtariGo
[Caz02b]
Tristan Cazenave. Comparative evaluation of strategies based on the values of direct threats. In Board Games in Academia V, Barcelona, 2002. [ http://www.ai.univ-paris8.fr/~cazenave/ts.pdf ]
Keywords: Threats, BMove, MaxMove, SenteQ, Thermostrat, HotStrat
[Caz02e]
Tristan Cazenave. Metarules to improve tactical Go knowledge. In Joint Conference on Information Sciences, Durham, NC, 2002. [ http://www.ai.univ-paris8.fr/~cazenave/jcis2002.pdf ]
Keywords: automatically generated rules databases, exceptions, metarules
[Caz03]
Tristan Cazenave. Recherche sélective et génération automatique de programmes. Habilitation thesis. Université Paris, 2003. In French. [ http://www.ai.univ-paris8.fr/~cazenave/habil.ps ]
[CH05b]
Tristan Cazenave and Bernard Helmstetter. Search for transitive connections. Information Sciences, 2005. [ http://www.ai.univ-paris8.fr/~cazenave/transitive-IS-final.pdf ]
Keywords: Transitivity, connections, generalized threats
[Caz04]
Tristan Cazenave. Generalized widening. In ECAI 2004, 2004. [ http://www.ai.univ-paris8.fr/~cazenave/openld.pdf ]
Keywords: Threat based search, Iterative Widening
[HC04]
Bernard Helmstetter and Tristan Cazenave. Incremental transpositions. In Computers and Games Conference 2004, Ramat-Gan, Israel, 2004. [ http://www.ai.univ-paris8.fr/~cazenave/it.pdf ]
Keywords: permutation of moves
[Caz05b]
Tristan Cazenave. The separation game. In JCIS 2005, 2005. [ http://www.ai.univ-paris8.fr/~cazenave/separation.pdf ]
[CH05a]
Tristan Cazenave and Bernard Helmstetter. Combining tactical search and Monte-Carlo in the game of Go. In IEEE CIG 2005, 2005. [ http://www.ai.univ-paris8.fr/~cazenave/searchmcgo.pdf ]
Keywords: Monte-Carlo, tactical goals
[Caz05a]
Tristan Cazenave. A Phantom Go program. In Advances in Computer Games 11, 2005. [ http://www.ai.univ-paris8.fr/~cazenave/phantomgo.pdf ]
Keywords: Phantom Go, Monte-Carlo
[CJ07]
Tristan Cazenave and Nicolas Jouandeau. On the parallelization of UCT. In CGW 2007, pages 93-101, June 2007. [ http://www.ai.univ-paris8.fr/~cazenave/parallelUCT.pdf ]
Keywords: UCT, parallelization
[cgj]
Computer Go. Published in cooperation with the American Go Association and the Canadian Go Association. [ http://www.daogo.org/ ]
[JI98]
Herik Jaap and Hiroyuku Iida, editors. Computers and Games, First International Conference, volume 1558 of Lecture Notes in Computer Science, Tsukuba, Japan, November 1998. Springer.
[JI00]
Herik Jaap and Hiroyuku Iida, editors. Computers and Games, Second International Conference, volume 2063 of Lecture Notes in Computer Science, Hamamatsu, Japan, October 2000. Springer.
[FMT+98]
Ian Frank, Hitoshi Matsubara, Morihiko Tajima, Atsushi Yoshikawa, Reijer Grimbergen, and Martin Müller, editors. Complex Games Lab Workshop. Electrotechnical Laboratory, Machine Inference Group, Tsukuba, Japan, November 1998. [ http://www.cs.ualberta.ca/~mmueller/cgo/cg98-workshop/cg98-workshop-papers.pdf ]
[Com]
The Computer-Go mailing list. [ http://computer-go.org/mailman/listinfo/computer-go  ]
[Cha96]
Horace Wai-kit Chan. Application of temporal difference learning and supervised learning in the game of Go. Master's thesis, Chinese University of Hong Kong, 1996. [ http://www.cs.cuhk.hk/~king/PUB/horace_thesis.ps.gz ]
Keywords: neural networks, temporal difference learning
[CKL96]
Horace Wai-Kit Chan, Irwin King, and John Lui. Performance analysis of a new updating rule for td(lambda) learning in feedforward networks for position evaluation in Go game. In IEEE International Conference on Neural Networks, volume 3, pages 1716-1720, 1996. [ http://www.cse.cuhk.edu.hk/~king/PUB/icnn96-tdgo.pdf ]
Keywords: neural networks, temporal difference learning
[GWJ+07]
Chaslot G.M.J.B., Winands M.H.M. Winands, Uiterwijk J.W.H.M., van den Herik H.J., and Bouzy B. Progressive strategies for Monte-Carlo tree search. Draft, submitted to JCIS workshop 2007, 2007. [ http://www.cs.unimaas.nl/g.chaslot/papers/pMCTS.pdf ]
Keywords: Monte Carlo, tree search, progressive bias, progressive unpruning, MANGO
[Che01a]
Keh-Hsun Chen. Computer Go: Knowledge, search, and move decision. ICGA, 24(4):203-215, 2001. [ http://www.coit.uncc.edu/drchen/Papers/ComputerGo.pdf ]
[Che01b]
Keh-Hsun Chen. A study of decision error in selective game tree search. Information Sciences, 135:177-186, 2001. [ http://www.coit.uncc.edu/drchen/Papers/DecisionError.pdf ]
Keywords: selective game tree search, heuristic evaluation, mini-max backup, decision error
[Che03]
Keh-Hsun Chen. Soft decomposition search and binary game forest model for move decision in Go. Information Sciences, 154:157-172, 2003. [ http://www.coit.uncc.edu/drchen/Papers/SoftDecomposition.pdf ]
Keywords: Combinatorial game theory, Soft decomposition search, Binary game forest, Temperature, Mean, Move-decision strategy
[CZZ+02]
X. Chen, D. Zhang, X. Zhang, Z. Li, X. Meng, S. He, and X. Hu. A functional MRI study of high-level cognition ii: The game of GO. Cognitive Brain Research, 2002. [ http://sheng-lab.psych.umn.edu/pdf_files/Chen_fMRI_GO.pdf ]
Keywords: Neural basis; Functional MRI; High-level cognition
[CCAD01]
Julian Churchill, Richard Cant, and David Al-Dabass. A new computational approach to the game of Go. In Game-On 2001 conference, 2001. [ http://ducati.doc.ntu.ac.uk/uksim/dad/webpagepapers/Game-14.pdf ]
Keywords: Computer Go, Neural Networks, Alpha beta search algorithms
[CVD03]
Heather Cook, Amanda Venghaus, and Peter Drake. Machine learning applied to the game of Go. Twelfth Regional Conference on Undergraduate Research, Murdock College Research Program. Conference poster, 2003. [ http://www.lclark.edu/~sciences/GOposter.pdf ]
Keywords: neural networks, machine learning, self play
[Cou06]
Rémi Coulom. Efficient selectivity and backup operators in Monte-Carlo tree search. Submitted to CG 2006, 2006. [ http://remi.coulom.free.fr/CG2006/CG2006.pdf ]
Keywords: Monte-Carlo, min-max, Crazy Stone
[Cou07]
Rémi Coulom. Computing Elo ratings of move patterns in the game of Go. Draft, submitted to ICGA Computer Games Workshop 2007, 2007. [ http://remi.coulom.free.fr/Amsterdam2007/MMGoPatterns.pdf ]
Keywords: Monte-Carlo, patterns, probability distribution, Bradley-Terry model, ELO, Crazy Stone
[CT00]
Marcel Crasmaru and John Tromp. Ladders are PSPACE-complete. In Jaap and Iida [JI00], pages 241-249. [ http://www2.is.titech.ac.jp/research/research-report/C/C-142.ps.gz ]
Keywords: Complexity of Go, Ladders, PSPACE-complete
[Dah]
Fredrik A. Dahl. Honte, a Go-playing program using neural nets. In Fürnkranz and Kubat [FK99]. [ http://www.ai.univie.ac.at/icml-99-ws-games/papers/dahl.ps.gz ]
Keywords: go, neural network, Honte
[DBG00]
Darryl Davis and Barnaby Berbank-Green. Towards an Architecture for A-life Agents II. IOS Press, 2000. [ http://www2.dcs.hull.ac.uk/NEAT/dnd/papers/nfici.pdf ]
[Dem01]
Erik D. Demaine. Playing games with algorithms: Algorithmic combinatorial game theory. In 26th Symposium on Mathematical Foundations in Computer Science (MFCS 2001), volume 2136 of Lecture Notes in Computer Science, pages 18-32, 2001. [ http://theory.lcs.mit.edu/~edemaine/papers/AlgGameTheoryMFCS2001/ ]
[DCC94]
Paul Donnelly, Patrick Corr, and Danny Crookes. Evolving Go playing strategy in neural networks, 1994. [ ftp://ftp-igs.joyjoy.net/Go/computer/egpsnn.ps.Z ]
Keywords: neural networks
[DM05]
David G Doshay and Charlie McDowell. Sluggo: A computer baduk program. In Third International Conference on Baduk. Myong-Ji University, Korea, October 2005. [ http://sluggo.dforge.cse.ucsc.edu/icob.pdf ]
Keywords: SlugGo, GNU Go
[DLVV04]
P. Drake, J. Levenick, L. Veenstra, and A. Venghaus. Pattern matching in the game of Go. Submitted, 2004. [ https://webdisk.lclark.edu/xythoswfs/webui/_xy-13652_1-tid_F5nG4R87 ]
[DSTV06]
Peter Drake, Niku Schreiner, Brett Tomlin, and Loring Veenstra. An efficient algorithm for eyespace classification in Go. In International Conference on Artificial Intelligence. CREA Press, 2006. [ http://www.lclark.edu/~drake/go/icai2006-final-drake.pdf ]
Keywords: graph theory, eyes
[DPSV07]
Peter Drake, Andrew Pouliot, Niku Schreiner, and Bjorn Vanberg. The proximity heuristic and an opening book in Monte Carlo Go. Submitted, 2007. [ https://webdisk.lclark.edu/xythoswfs/webui/_xy-2352013_1-t_Gct7yJ5s%22 ]
Keywords: Monte Carlo, UCT, Orego
[DU07a]
Peter Drake and Steve Uurtamo. Heuristics in Monte Carlo Go. In Proceedings of the 2007 International Conference on Artificial Intelligence. CSREA Press, 2007. [ https://webdisk.lclark.edu/xythoswfs/webui/_xy-2793610_1-t_RYPP7Zcz ]
Keywords: Monte Carlo, UCT, heuristics
[DU07b]
Peter Drake and Steve Uurtamo. Move ordering vs heavy playouts: Where should heuristics be applied in Monte Carlo Go? In Proceedings of the 3rd North American Game-On Conference, 2007. [ https://webdisk.lclark.edu/drake/publications/GAMEON-07-drake.pdf ]
Keywords: Monte Carlo, UCT, heuristics
[Dye95e]
Dave Dyer. Searches, tree pruning and tree ordering in Go. In 2nd Game Programming Workshop in Japan, Kanagawa, 1995. [ http://www.andromeda.com/people/ddyer/go/search.html ]
Keywords: search, pruning, alpha-beta, heuristic, ordering
[Dye95b]
Dave Dyer. An eye shape library for computer Go, 1995. draft, available from the author's homepage. [ http://www.andromeda.com/people/ddyer/go/shape-library.html ]
Keywords: eye shapes, database
[Dye95d]
Dave Dyer. Scoring completed games, 1995. Draft, avaliable from the author's homepage. [ http://www.andromeda.com/people/ddyer/go/scoring-games.html ]
Keywords: scoring
[Dye95c]
Dave Dyer. Global evaluation strategies in Go, 1995. Draft, avaliable from the author's homepage. [ http://www.andromeda.com/people/ddyer/go/global-eval.html ]
Keywords: global evaluation
[Dye95f]
Dave Dyer. Signatures for Go game records, 1995. Draft, avaliable from the author's homepage. [ http://www.andromeda.com/people/ddyer/go/signature-spec.html ]
[Dye95a]
Dave Dyer. Building a joseki dictionary from professional games, 1995. Draft, avaliable from the author's homepage. [ http://www.andromeda.com/people/ddyer/go/joseki-dictionary.html ]
Keywords: joseki library
[Eis97]
Bart Eisenberg. Kasparov, deep blue, and the games machines play. Pacific Connection, 8, 1997. [ http://www.gihyo.co.jp/SD/pacific/SD_9708.html ]
[Ekk03]
Reindert-Jan Ekker. Reinforcement learning and games. Master's thesis, Rijksuniversiteit Groningen, 2003. [ http://members.home.nl/r.j.ekker/afstudeer/tekst.pdf ]
Keywords: neural networks, reinforcement learning, 5x5 Go, temporal difference learning
[EvdWS04]
R. Ekker, E.C.D. van der Werf, and L.R.B. Schomaker. Dedicated TD-learning for stronger gameplay: applications to Go. In A. Nowe, T. Lennaerts, and K. Steenhaut, editors, Proceedings of Benelearn 2004 Annual Machine Learning Conference of Belgium and The Netherlands, pages 46-52, 2004. [ http://members.home.nl/r.j.ekker/afstudeer/paper_benelearn04.pdf ]
Keywords: Temporal-difference learning, TD(mu), TD-leaf, TD-directed, residual algorithms
[End91]
Herbert Enderton. The Golem Go program. Technical Report CMU-CS-92-101, School of Computer Science, Carnegie-Mellon University, 1991. [ ftp://ftp-igs.joyjoy.net/Go/computer/golem.sh.Z ]
Keywords: go, Golem, neural networks, relaxation
[Enz96]
Markus Enzenberger. The integration of a priori knowledge into a Go playing neural network, 1996. Available by Internet. [ http://www.cs.ualberta.ca/~emarkus/neurogo/neurogo.ps.gz ]
Keywords: go, neural network, NeuroGo, learning
[Enz03]
Markus Enzenberger. Evaluation in Go by a neural network using soft segmentation. In 10th Advances in Computer Games conference, pages 97-108, 2003. [ http://www.cs.ualberta.ca/~emarkus/neurogo/neurogo3.pdf ]
Keywords: neural networks, segmentation, connectivity, NeuroGo
[Epp96]
David Eppstein. Dynamic connectivity in digital images. Technical Report TR 96-13, ICS, UCI, 1996. [ http://www.ics.uci.edu/~eppstein/pubs/all.html ]
Keywords: dynamic planar connectivity, percolation, lower bounds, image processing, go, lines of action
[FMW05]
Christopher Fellows, Yuri Malitsky, and Gregory Wojtaszczyk. GoNN - incorporating a neural network into the game of Go. AI Project, CS 473, Cornell University, 2005. [ http://www.people.cornell.edu/pages/ynm2/Papers/Incorporating a Neural Net into the Game of Go - Final Report.pdf ]
[FMW06]
Christopher Fellows, Yuri Malitsky, and Gregory Wojtaszczyk. Exploring GnuGo's evaluation function with a SVM. AAAI-06 student posters, 2006. [ http://www.people.cornell.edu/pages/ynm2/Papers/AAAI06 - Exploring GnuGos Evaluation Function with a SVM.pdf ]
Keywords: GNU Go, Support Vector Machine
[Fot93]
David Fotland. Knowledge representation in The Many Faces of Go, 1993. Available by Internet. [ ftp://ftp-igs.joyjoy.net/Go/computer/mfg.tex.Z ]
Keywords: Many Faces of Go
[Fra00]
William Edward Fraser. Thermographic analysis of Go endgames using brute force. Combinatorial Game Theory Workshop, July 2000. [ http://www.msri.org/publications/ln/msri/2000/gametheory/fraser/1/banner/01.html ]
Keywords: Thermographs
[FK99]
Johannes Fürnkranz and Miroslav Kubat, editors. Workshop Notes: Machine Learning in Game Playing. 16th International Conference on Machine Learning (ICML-99), Bled, Slovenia, 1999. [ http://www.ai.univie.ac.at/icml-99-ws-games ]
Keywords: go, machine learning
[F01]
Johannes Fürnkranz. Machine learning in games: A survey. Nova Science Publishers, Huntington, NY, 2001. To appear. [ http://www.ai.univie.ac.at/cgi-bin/tr-online?number+2000-31 ]
Keywords: Machine Learning, Game Playing
[GWMT06]
Sylvain Gelly, Yizao Wang, Rémi Munos, and Olivier Teytaud. Modification of UCT with patterns in Monte-Carlo Go. Technical Report 6062, INRIA, France, November 2006. [ http://hal.inria.fr/docs/00/12/15/16/PDF/RR-6062.pdf ]
Keywords: UCT, UCB1, Monte-Carlo, MoGo
[GW06]
Sylvain Gelly and Yizao Wang. Exploration exploitation in Go: UCT for Monte-Carlo Go, December 2006. [ http://eprints.pascal-network.org/archive/00002713/01/nips_exploration_exploitation.pdf ]
Keywords: Monte Carlo, UCT, MoGo
[GS07]
Sylvain Gelly and David Silver. Combining online and offline knowledge in UCT. In International Conference on Machine Learning, ICML 2007, 2007. [ http://www.machinelearning.org/proceedings/icml2007/papers/387.pdf ]
Keywords: UCT, offline knowledge, default policy, Rapid Action Value Estimation, RAVE, RLGO
[Gel07]
Sylvain Gelly. A Contribution to Reinforcement Learning; Application to Computer-Go. PhD thesis, Université Paris-Sud, 2007. [ http://www.lri.fr/~gelly/paper/SylvainGellyThesis.pdf ]
Keywords: MoGo, UCT, RAVE
[Gho04]
Imran Ghory. Reinforcement learning in board games. Technical Report CSTR-04-004, Department of Computer Science, University of Bristol, May 2004. [ http://www.cs.bris.ac.uk/Publications/Papers/2000100.pdf ]
Keywords: TD-Learning
[GGKH00]
Thore Graepel, Mike Goutrie, Marco Krüger, and Ralf Herbrich. Go, SVM, Go, 2000. [ http://stat.cs.tu-berlin.de/~ralfh/go.ps.gz ]
Keywords: Go, Machine Learning, Common Fate Graph, Relative Subgraph Features, Support Vector Machine, Kernel Perceptron, Tsume Go, 9x9
[GGKH01]
Thore Graepel, Mike Goutrie, Marco Krüger, and Ralf Herbrich. Learning on graphs in the game of Go. In International Conference on Artificial Neural Networks (ICANN-01), Vienna, Austria, 2001. [ http://research.microsoft.com/~rherb/papers/graegoukrueher01.ps.gz ]
Keywords: CFG, common fate graph, learning, SVM, support vector machine, kernel perceptron, life-and-death
[Gra02]
Thore Graepel. PAC-Bayesian Pattern Classification with Kernels: Theory, Algorithms, and an Application to the Game of Go. PhD thesis, Department of Computer Science, Technical University of Berlin, Berlin, Germany, 2002. [ http://edocs.tu-berlin.de/diss/2002/graepel_thore.pdf ]
Keywords: pattern classification, machine learning, kernel methods, PAC-Bayesian framework, support vector machines, common fate graph
[SHG06]
David Stern, Ralf Herbrich, and Thore Graepel. Bayesian pattern ranking for move prediction in the game of Go. In International Conference on Machine Learning (ICML-2006), 2006. [ http://www.icml2006.org/icml_documents/camera-ready/110_Bayesian_Pattern_Ran.pdf ]
Keywords: Automatic pattern learning, move prediction, Go player, Bayesian learning, expert games
[Gre95]
Jeffrey Greenberg. Programming Go by breeding software, 1995. Available by Internet. [ http://www.inventivity.com/OpenGo/Papers/jeffg/breed.html ]
Keywords: genetic programming
[Gre97]
Jeffrey Greenberg. Architecture of a Go programming environment, 1997. Available from the author's homepage. [ http://www.concentric.net/~Jgberg/env.html ]
[Har03]
Matthew Harren. Federations in Go endgames. Available by Internet, December 2003. Term project, MATH 275 (Professor Elwyn Berlekamp), University of California, Berkeley. [ http://www.cs.berkeley.edu/~matth/analgo/Federations.html ]
Keywords: combinatorial game theory, dependency, subgames
[Hol]
Arno Hollosi. SGF file format FF[4]. Smart game format specification. Available by Internet. [ http://www.red-bean.com/sgf/ ]
Keywords: sgf, file format, saving, games, records, FF[4]
[Hua02]
Tim Huang. Towards a probabilistic model for intent inference in the game of Go. In AAAI Fall Symposium on Intent Inference for Users, Teams and Adversaries, 2002. [ http://www.cs.middlebury.edu/~huang/publications/aaaifs2002.pdf ]
Keywords: opponent modeling, intent inference, probabilistic approach
[HCM04]
Tim Huang, Graeme Connell, and Bryan McQuade. Experiments with learning opening strategy in the game of Go. International Journal on Artificial Intelligence Tools, 13(1):101-104, 2004. [ http://www.cs.middlebury.edu/~huang/publications/ijait2004.pdf ]
Keywords: temporal difference learning, self-play
[Hui00]
Antti Huima. A group-theoretic Zobrist hash function, 2000. [ http://fragrieu.free.fr/zobrist.pdf ]
Keywords: Zobrist, hash function, hash key, hash table, efficient, color, rotation, mirroring
[Joh97]
George Johnson. To test a powerful computer, play an ancient game. The New York Times, July 29 1997. [ http://mechner.com/david/compgo/times/ ]
Keywords: David Mechner
[Kam02]
Piotr Kaminski. Las Vegas Go. Available by Internet., 2002. [ http://www.ideanest.com/vegos/LasVegasGo.pdf ]
Keywords: Monte Carlo Go, simulated annealing, Gobble, Vegos
[Kaw03]
Ryuichi Kawa. Inside Haruka. CGF (Computer Go Forum) Journal Vol 5, 2003. In Japanese. [ http://www.cs.ualberta.ca/~games/go/seminar/2003/031103/vol5-4.pdf ]
[KYH04]
Graham Kendall, Razali Yaakob, and Philip Hingston. An investigation of an evolutionary approach to the opening of Go. In Proceedings of the 2004, IEEE Congress on Evolutionary Computation (CEC'04), 2004. [ http://www.scis.ecu.edu.au/research/wfg/publications/WFG2004b.pdf ]
Keywords: neural networks, evolutionary strategy, Gondo
[KM03b]
Akihiro Kishimoto and Martin Müller. A solution to the GHI problem for depth-first proof-number search. In 7th Joint Conference on Information Sciences (JCIS2003), pages 489-492, 2003. [ http://www.cs.ualberta.ca/~kishi/gps_file/kishi_mueller_jcis.ps.gz ]
Keywords: Graph history interaction, Df-pn
[KM03a]
Akihiro Kishimoto and Martin Müller. Df-pn in Go: An application to the one-eye problem. In Advances in Computer Games 10, pages 125-141. Kluwer Academic Publishers, 2003. [ http://www.cs.ualberta.ca/~kishi/pdf_file/acg_kishimoto_mueller.pdf ]
Keywords: proof-number search, df-pn, one-eye problem
[KM04]
Akihiro Kishimoto and Martin Müller. A general solution to the graph history interaction problem. In Nineteenth National Conference on Artificial Intelligence (AAAI'04), pages 644-649. AAAI Press, 2004. [ http://www.cs.ualberta.ca/~kishi/pdf_file/AAAI04KishimotoA.pdf ]
Keywords: GHI problem, df-pn algorithm, alpha-beta algorithm, Kawano's simulation
[Kis05]
Akihiro Kishimoto. Correct and Efficient Search Algorithms in the Presence of Repetitions. PhD thesis, University of Alberta, January 2005. [ http://www.cs.ualberta.ca/~kishi/pdf_file/kishi_phd_thesis.pdf ]
Keywords: Search, repetitions, One-eye problem, Tsume-Go, checkers, graph history interaction, GHI, proof-number search, df-pn
[KM05b]
Akihiro Kishimoto and Martin Müller. Dynamic Decomposition Search: A Divide and Conquer approach and its application to the one-eye problem in Go. In IEEE Symposium on Computational Intelligence and Games (CIG'05), pages 164-170, 2005. [ http://www.cs.ualberta.ca/~kishi/pdf_file/kishi_mueller_cig05.pdf ]
[KM05a]
A. Kishimoto and M. Müller. Search versus knowledge for solving life and death problems in Go. In Twentieth National Conference on Artificial Intelligence (AAAI-05), pages 1374-1379, 2005. [ http://www.cs.ualberta.ca/~mmueller/ps/aaai05-tsumego.pdf ]
Keywords: Life and Death, tsume-Go, TSUMEGO EXPLORER, GoTools
[YYK+06]
Haruhiro Yoshimoto, Kazuki Yoshizoe, Tomoyuki Kaneko, Akihiro Kishimoto, and Kenjiro Taura. Monte Carlo has a way to Go. In Twenty-First National Conference on Artificial Intelligence (AAAI-06), 2006. [ http://www.fun.ac.jp/~kishi/pdf_file/AAAI06YoshimotoH.pdf ]
Keywords: Monte Carlo, parallelizing
[KM96]
Tim Klinger and David A. Mechner. An architecture for Go, 1996. [ http://mechner.com/david/compgo/acg/ ]
Keywords: incremental
[Kli01]
Tamir Klinger. Adversarial Reasoning: A Logical Approach for Computer Go. PhD thesis, New York University, 2001. [ http://mechner.com/david/compgo/thesis.pdf ]
Keywords: knowledge-based program, life and death, goal theory, modal logic, strategic theories
[KS06]
Levente Kocsis and Csaba Szepesvári. Bandit based monte-carlo planning. In ECML-06, 2006. [ http://zaphod.aml.sztaki.hu/papers/ecml06.pdf ]
Keywords: Monte-Carlo, planning, UCT
[Koj99]
Takuya Kojima. Knowledge acquisition from game records. In Fürnkranz and Kubat [FK99]. [ http://www.ai.univie.ac.at/icml-99-ws-games/papers/kojima.ps.gz ]
[GKO02]
Dylan Shell George Konidaris and Nir Oren. Evolving neural networks for the Capture Game. SAICSIT Postgraduate Symposium 2002, 2002. [ http://www-robotics.usc.edu/~dshell/res/evneurocapt.pdf ]
Keywords: Genetic algorithm, neural networks, Capture game, Atari-Go
[Kun02]
Daniel R. Kunkle. The game of Go and multiagent systems. Technical report, Rochester Institute of Technology, Rochester NY, 2002. [ http://www.redfish.com/dkunkle/mypapers/goAndMultiagents.pdf ]
Keywords: multiagent systems, autonomous agents
[Lan96]
Howard Landman. Eyespace Values in Go, pages 227-257. Cambridge University Press, 1996. [ http://www.msri.org/publications/books/Book29/files/landman.pdf ]
Keywords: go, combinatorial game theory, life-and-death, eyes
[BDL03]
Jacky Baltes Byung-Doo Lee, Hans Werner Guesgen. The application of td(lambda) learning to the opening games of 19x19 Go. Technical Report CITR-TR-136, University of Auckland, 2003. [ http://www.citr.auckland.ac.nz/techreports/2003/CITR-TR-136.pdf ]
[Lee04]
Byung-Doo Lee. Life-and-death problem solver in go. Technical Report CITR-TR-145, University of Auckland, 2004. [ http://www.citr.auckland.ac.nz/techreports/2004/CITR-TR-145.pdf ]
[PL06]
Jakub Pawlewicz and Lukasz Lew. Improving depth-first PN-search: 1 + e trick. In 5th International Conference on Computers and Games, Turin, Italy, 2006. [ http://www.mimuw.edu.pl/~lew/download.php?file_no=6 ]
Keywords: PN-Search, DF-PN, PDS, Atari Go
[LM01]
Alex Lubberts and Risto Miikkulainen. Co-evolving a Go-playing neural network, 2001. [ ftp://ftp.cs.utexas.edu/pub/neural-nets/papers/lubberts.coevolution-gecco01.ps.gz ]
Keywords: neural networks, competitive fitness sharing, shared sampling, hall of fame, SANE, co-evolution
[MIG]
Hitoshi Matsubara, Hiroyuki Iida, and Reijer Grimbergen. Chess, shogi, Go, natural developments in game research. [ http://citeseer.nj.nec.com/matsubara97ches.html ]
[MM05]
H. A. Mayer and Peter Maier. Coevolution of neural Go players in a cultural environment. In Proceedings of the Congress on Evolutionary Computation 2005, Edinburgh, Scotland, 2005. [ http://www.cosy.sbg.ac.at/~helmut/Research/Papers/edinburgh05.pdf ]
Keywords: genetic algorithms, evolutionary computing, neural networks
[May07]
Helmut A. Mayer. Board representations for neural Go players learning by temporal difference. In IEEE Symposium on Computational Intelligence and Games CIG 2007, 2007. [ http://www.cosy.sbg.ac.at/~helmut/Research/Papers/honolulu07.pdf ]
Keywords: neural networks, temporal difference learning, board representation
[Mec98]
David Mechner. All systems Go. The Sciences, 38(1), 1998. [ http://mechner.com/david/compgo/sciences/ ]
[MK01a]
Alex B. Meijer and Henk Koppelaar. A learning architecture for the game of Go. In 2nd International Conference on Intelligent Games and Simulation (GAMEON 2001), London, 2001. [ http://mmi.tudelft.nl/~meijer/files/meijer-gameon01 ]
Keywords: learning, HUGO, subgames, sente, fuzzy partial ordering
[MK01b]
Alex B. Meijer and Henk Koppelaar. Pursuing abstract goals in the game of Go. In 13th Belgium-Netherlands Conference on Artificial Intelligence (BNAIC 2001), Amsterdam, 2001. [ http://mmi.tudelft.nl/~meijer/files/meijer-bnaic01.pdf ]
Keywords: adversarial planning, search, goal-checking
[MK03]
Alex B. Meijer and Henk Koppelaar. Towards multi-objective game theory - with application to Go. In Game-On 2003, 4th Intl. Conf. on Intelligent Games and Simulation, 2003. [ http://mmi.tudelft.nl/~meijer/files/meijer-gameon03.pdf ]
Keywords: Combinatorial Games, Multiple Objectives, Computational Intelligence, Dependence of Games, Threat, Ko
[Moe93]
David Moews. On Some Combinatorial Games Connected with Go. PhD thesis, University of California, Berkeley, 1993. [ http://xraysgi.ims.uconn.edu:8080/dmoews/thesis.ps ]
Keywords: Combinatorial Game Theory, Ko
[Moe96]
David Moews. Loopy Games and Go, pages 259-272. Cambridge University Press, 1996. [ http://www.msri.org/publications/books/Book29/files/moloopy.pdf ]
Keywords: go, combinatorial, loopy
[MP95]
Matthias Müller-Prove. Lebende Blöcke beim Go - ein formaler Ansatz unter Verwendung von Petri-Netzen, 1995. In German. [ http://www.mprove.de/script/95/studienarbeit/Studienarbeit.pdf ]
[M91a]
Martin Müller. Measuring the performance of Go programs. International Go Congress, Beijing, 1991. [ http://www.cs.ualberta.ca/~mmueller/ps/mueller91a.ps ]
Keywords: rating
[M91b]
Martin Müller. Pattern matching in explorer. Game Playing System Workshop, ICOT, Tokyo, 1991. [ http://www.cs.ualberta.ca/~mmueller/ps/mueller91b.ps ]
Keywords: Explorer, pattern matching
[M93]
Martin Müller. Game theories and computer Go. Go and Computer Science Workshop (GCSW'93), INRIA, Sophia-Antipolis, 1993. [ http://www.cs.ualberta.ca/~mmueller/ps/mueller93.ps ]
Keywords: combinatorial game theory,
[M95]
Martin Müller. Computer Go as a Sum of Local Games: An Application of Combinatorial Game Theory. PhD thesis, ETH Zürich, 1995. [ ftp://ftp.inf.ethz.ch/pub/publications/dissertations/th11006.ps.gz ]
Keywords: combinatorial game theory, Smart game board, board partition, unconditional life
[MG96]
Martin Müller and Ralph Gasser. Experiments in Computer Go Endgames, pages 273-284. Cambridge University Press, 1996. [ http://www.msri.org/publications/books/Book29/files/muller.pdf ]
Keywords: go, endgame, ko, explorer
[MBS96]
Martin Müller, Elwyn Berlekamp, and Bill Spight. Generalized thermography: Algorithms, implementation, and application to Go endgames. Technical Report 96-030, ICSI, Berkeley, 1996. [ http://www.cs.ualberta.ca/~mmueller/ps/tr-96-030a.ps.gz ]
Keywords: thermography, combinatorial game theory, Ko
[M97]
Martin Müller. Playing it safe: Recognizing secure territories in computer Go by using static rules and search. In Game Programming Workshop in Japan '97, MATSUBARA, H. (ed.), Computer Shogi Association, Tokyo, Japan, 1997. [ http://www.cs.ualberta.ca/~mmueller/ps/gpw97.ps.gz ]
Keywords: static, search, unconditional life
[M98]
Martin Müller. Computer Go: A Research Agenda, pages 252-264. Volume 1558 of Jaap and Iida [JI98], November 1998. [ http://www.cs.ualberta.ca/~mmueller/ps/cg1998.ps.gz ]
Keywords: Review
[M99c]
Martin Müller. Partial order bounding: Using partial order evaluation in game tree search. Technical Report TR-99-12, Electrotechnical Laboratory, Tsukuba, Japan, 1999. [ http://www.cs.ualberta.ca/~mmueller/ps/TR9912.ps.gz ]
Keywords: partial order bounding, semeai
[M99a]
Martin Müller. Computer Go: A research agenda. ICCA Journal, 22(2):104-112, 1999. [ http://www.cs.ualberta.ca/~mmueller/ps/icca1999.ps ]
[M99b]
Martin Müller. Decomposition search: A combinatorial games approach to game tree search, with applications to solving Go endgames. In IJCAI-99, volume 1, pages 578-583, 1999. [ http://www.cs.ualberta.ca/~mmueller/ps/ijcai1999.ps.gz ]
Keywords: decomposition search, combinatorial game theory
[M99d]
Martin Müller. Proof-set search. Technical Report TR-99-20, Electrotechnical Laboratory, Tsukuba, Japan, 1999. [ http://www.cs.ualberta.ca/~mmueller/ps/pss-tr01-09.ps.gz ]
Keywords: proof-set serach, transposition, proof-number search
[M99e]
Martin Müller. Race to capture: Analyzing semeai in Go. In Game Programming Workshop in Japan '99, MATSUBARA, H. (ed.), Computer Shogi Association, Tokyo, Japan, 1999. [ http://www.cs.ualberta.ca/~mmueller/ps/gpw99.ps.gz ]
Keywords: capturing race, semeai
[M00a]
Martin Müller. Not like other games - why tree search in Go is different. In Fifth Joint Conference on Information Sciences (JCIS 2000), 2000. Extended abstract, invited paper for special session on Heuristic Search and Computer Game Playing. To appear. [ http://www.cs.ualberta.ca/~mmueller/ps/jcis2000.ps.gz ]
Keywords: minimax, search, pass, ko, terminal position
[M00b]
Martin Müller. Review: Computer Go 1984-2000. In Jaap and Iida [JI00], pages 405-413. [ http://www.cs.ualberta.ca/~mmueller/ps/CGGo2000.ps.gz ]
Keywords: Review, Go programs
[M02]
Martin Müller. Computer Go. Artificial Intelligence, 134:145-179, 2002. [ http://www.cs.ualberta.ca/~mmueller/ps/Go2000.ps.gz ]
Keywords: survey
[M01a]
Martin Müller. Global and local game tree search. Information Sciences, 135:187-206, 2001. The URL links to an older version of the article. [ http://www.cs.ualberta.ca/~mmueller/ps/mueller-infsci2000.ps.gz ]
Keywords: Local search, Game tree search, Decomposition search, Combinatorial game theory
[M01b]
Martin Müller. Partial order bounding: A new approach to evaluation in game tree search. Artificial Intelligence, 129(1-2):279-311, 2001. [ http://www.cs.ualberta.ca/~mmueller/ps/mueller-aij-rev2.ps.gz ]
Keywords: game tree search, partial order evaluation, partial order bounding
[M]
Martin Müller. Multicriteria evaluation in computer game-playing, and its relation to AI planning. In Drabble et al. [DKR02]. [ http://www.laas.fr/aips/ws-tu1.pdf ]
Keywords: planning
[MES04]
Martin Müller, Markus Enzenberger, and Jonathan Schaeffer. Temperature discovery search. In 19th National Conference on Artificial Intelligence (AAAI 2004), pages 658-663, San Jose, CA, 2004. [ http://www.cs.ualberta.ca/~mmueller/ps/AAAI104MullerM.pdf ]
Keywords: Temperature Discovery Search, combinatorial games, alpha-beta algorithm, Go, Amazons
[PAC07]
Rémi Munos Pierre-Arnaud Coquelin. Bandit algorithms for tree search. In 23rd Conference on Uncertainty in Artificial Intelligence, UAI 2007, University of British Columbia, Vancouver, May 2007. [ http://hal.inria.fr/docs/00/15/02/07/PDF/BAST.pdf ]
Keywords: UCT, Flat-UCB, BAST, Bandit Algorithm for Smooth Trees
[Nag98]
Ayumu Nagai. A new and/or tree search algorithm using proof number and disproof number. In Ian Frank, Hitoshi Matsubara, Morihiko Tajima, Atsushi Yoshikawa, Reijer Grimbergen, and Martin Müller, editors, Complex Games Lab Workshop. Electrotechnical Laboratory, Machine Inference Group, Tsukuba, Japan, 1998. [ http://www.cs.ualberta.ca/~mmueller/cgo/cg98-workshop/Nagai.pdf ]
Keywords: search, proof number, PDS
[Nak97]
Teigo Nakamura. Acquisition of move sequence patterns from game record database using n-gram statistics. In Game Programming Workshop 97, 1997. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/gpw97.pdf ]
[NK99a]
Teigo Nakamura and Takashi Kajiyama. Automatic acquisition of move sequence patterns from encoded strings of Go moves. In Game Informatics, volume GI-1-15, 1999. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/gi99.pdf ]
[NK99b]
Teigo Nakamura and Takashi Kajiyama. Constructing a stochastic model for encoded strings of Go moves. In Game Programming Workshop, 1999. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/gpw99.pdf ]
[NK00b]
Teigo Nakamura and Takashi Kajiyama. Feature extraction from encoded texts of moves and categorization of game records. In Game Informatics, volume GI-2-11, 2000. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/gi00a.pdf ]
[NK00a]
Teigo Nakamura and Takashi Kajiyama. Acquisition of sequence patterns and their co-occurrence relations from game records of Go. In Game Informatics, volume GI-4-10, 2000. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/gi00b.pdf ]
[NB02]
Teigo Nakamura and Elwyn Berlekamp. Analysis of composite corridors. Technical Report TR-02-005, International Computer Science Institute, Berkeley, February 2002. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/tr-02-005.pdf ]
Keywords: Combinatorial game theory, corridors, decomposition, multiple invasions theorem
[Nak02]
Teigo Nakamura. Analysis of ko. Draft. Available from the author's homepage, 2002. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/KoAnalysis.txt ]
[Nak03a]
Teigo Nakamura. Analysis of capturing races with shared liberties. In Game Programming Workshop 2003, 2003. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/gpw03.pdf ]
[Nak03b]
Teigo Nakamura. Brief introduction to the papers about Go in 2002. CGF Journal Vol.5, 2003. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/article2.pdf ]
[Nak03c]
Teigo Nakamura. Combinatorial game theory and the game of Go - analyzing semeai. CGF Journal, 5, 2003. In Japanese. [ http://www.dumbo.ai.kyutech.ac.jp/htdocs/teigo-ken/teigo/GoResearch/article1.pdf ]
[Nak05]
Teigo Nakamura. On counting liberties in capturing races of Go. BIRS Combinatorial Game Theory Workshop; Presentation slides, June 2005. [ http://www.dumbo.ai.kyutech.ac.jp/~teigo/GoResearch/cgtw05banff.pdf ]
[NL02]
Andrea Naica-Loebell. Grosartiges Testumfeld für künstliche Intelligenz, 2002. In German. [ http://heise.de/tp/deutsch/inhalt/lis/12325/1.html ]
Keywords: Michael Reiss, Martin Mueller, Bruno Bouzy
[Nij06]
Emil H.J. Nijhuis. Learning patterns in the game of Go. Master's thesis, Universiteit van Amsterdam, December 2006. [ http://www.science.uva.nl/research/ias/alumni/m.sc.theses/theses/EmilNijhuis.pdf ]
Keywords: Support Vector Machines, Common Fate Graph
[Niu04]
Xiaozhen Niu. Recognizing safe territories and stones in computer Go. Master's thesis, Department of Computing Science, University of Alberta, 2004. [ http://www.cs.ualberta.ca/~games/go/seminar/notes/040225/thesis.pdf ]
Keywords: Safety solver, search, region-merging, weakly dependent regions, Explorer, GNU Go
[NM04]
Xiaozhen Niu and Martin Müller. An improved safety solver for Computer Go. In Computers and Games 2004, Ramat-Gan, Israel, 2004. [ http://www.cs.ualberta.ca/~games/go/seminar/notes/040225/safety.pdf ]
Keywords: safety, territory, exact, regions
[NKM05]
Xiaozhen Niu, Akihiro Kishimoto, and Martin Müller. Recognizing seki in computer Go. In 11th Advances in Computer Games Conference, 2005. [ http://www.cs.ualberta.ca/~mmueller/ps/seki.pdf ]
Keywords: Seki, local search, global-level static analysis
[NM06]
Xiaozhen Niu and Martin Müller. An open boundary safety-of-territory solver for the game of Go. In 5th Conference on Computer and Games, CG2006, 2006. [ http://www.cs.ualberta.ca/~mmueller/ps/safetysolver2.pdf ]
Keywords: safety solver, open boundary problems
[PK05]
Hyun-Soo Park and Kyung-Woo Kang. Evaluation of strings in computer Go using articulation points check and seki judgment. LNAI, 3089, 2005. [ http://203.246.74.213/38090197.pdf ]
Keywords: String Graph, Articulation Points, Seki, Evaluation
[Pel91]
Barney Pell. Exploratory learning in the game of Go. In Heuristic Programming in Artificial Intelligence 2: The 2nd Computer Olympiad. Ellis-Horwood, 1991. [ http://www.cl.cam.ac.uk/ftp/papers/reports/TR275-bdp-go.ps.gz ]
Keywords: go, learning, exploration, probability
[PB01]
Andres Santiago Perez-Bergquist. Applying ESP and region specialists to neuro-evolution for Go. Technical Report CS-TR-01-24, The University of Texas at Austin, Department of Computer Sciences, 2001. [ http://www.cs.utexas.edu/ftp/pub/techreports/tr01-24.pdf ]
Keywords: Neural networks, ESP, SANE, GnuGo.
[Pur03]
Dev Purkayastha. Survey and synthesis of Go-playing agents. Available by Internet., 2003. [ http://www.people.fas.harvard.edu/~purkayas/go-survey.pdf ]
[Rai04]
Tapani Raiko. The Go-playing program called Go81. In Proceedings of the Finnish Artificial Intelligence Conference, STeP 2004, 2004. [ http://www.cis.hut.fi/praiko/papers/go_step.pdf ]
Keywords: Go, swarm intelligence, PalmOS
[Rai05]
Tapani Raiko. Nonlinear relational Markov networks with an application to the game of Go. In 15th International Conference on Artificial Neural Networks, ICANN 2005, pages 989-996, 2005. [ http://www.cis.hut.fi/praiko/papers/icann05.pdf ]
Keywords: joint probabilistic model, relational database, discrete and continuous attributes, relational Markov networks
[LR05]
P. Baldi L. Ralaivola, L. Wu. SVM and pattern-enriched common fate graphs for the game of Go. In European Symposium on Artificial Neural Networks, Bruges, Belgium, 2005. [ http://eprints.pascal-network.org/archive/00001460/01/gopaper.pdf ]
Keywords: common fate graph, support vector machine
[RFB00]
Jan Ramon, Tom Francis, and Hendrik Blockeel. Learning a Go heuristic with Tilde. In Jaap and Iida [JI00], pages 151-169. [ http://www.cs.kuleuven.ac.be/~janr/ ]
Keywords: Machine Learning, Go, Decision trees, Inductive Logic Programming, Tsume-Go
[RB01]
Jan Ramon and Hendrik Blockeel. A survey of the application of machine learning to the game of Go. In Hahn and Sang-Dae, editors, First International Conference on Baduk, pages 1-10. Myong-ji University, Korea, May 2001. [ http://www.cs.kuleuven.ac.be/~dtai/publications/files/36228.ps.gz ]
Keywords: Machine learning, inductive logic programming
[RJB02]
Jan Ramon, Nico Jacobs, and Hendrik Blockeel. Opponent modeling by analysing play. In M. Bowling, G. Kaminka, and R. Vincent, editors, Proceedings of Workshop on agents in computer games, 2002. [ http://www.cs.kuleuven.ac.be/~dtai/publications/files/38667.ps.gz ]
Keywords: Opponent modeling, logical decision tree learning system, Tilde
[RS03]
J. Ramon and J. Struyf. Computer science issues in Baduk. In N. Chihyung, editor, Proceedings of the 2nd International Conference on Baduk, pages 163-182, 2003. [ http://www.cs.kuleuven.ac.be/~dtai/publications/files/40886.pdf ]
Keywords: Internet Go
[RC04]
J. Ramon and T. Croonenborghs. Searching for compound goals using relevancy zones in the game of Go. In J. van den Herik, Y. Bjornsson, and N. Netanyahu, editors, Fourth International Conference on Computers and Games, Ramat-Gan, Israel, 2004. [ http://www.cs.kuleuven.ac.be/~dtai/publications/files/41320.ps.gz ]
Keywords: search, relevancy zone, compund goals
[RMM96]
Norman Richards, David Moriarty, and Risto Miikkulainen. Evolving neural networks to play Go. Applied Intelligence, 1996. [ http://www.xs4all.nl/~janrem/Artikelen/richards.apin97.ps.gz ]
Keywords: neural networks, SANE
[RB95]
Christopher D. Rosin and Richard K. Belew. Methods for competitive co-evolution: Finding opponents worth beating. In 6th International Conference on Genetic Algorithms. L.J. Eshelman, ed., 1995. [ http://www-cse.ucsd.edu/users/crosin/ ]
Keywords: competitive co-evolution, cellular automata, learning, fitness
[Ros97]
Christopher Rosin. Coevolutionary Search Among Adversaries. PhD thesis, University of California, San Diego, 1997. [ http://www-cse.ucsd.edu/users/crosin/ ]
Keywords: coevolution, fitness
[RL05]
Thomas Philip Runarsson and Simon Lucas. Co-evolution versus self-play temporal difference learning for acquiring position evaluation in small-board Go. IEEE Transactions on Evolutionary Computation, 9, December 2005. [ http://cerium.raunvis.hi.is/~tpr/papers/RuLu05.pdf ]
[Rut00]
Per Rutquist. Evolving an evaluation function to play Go. Master's thesis, Ecole Polytechnique, 2000. [ http://www.eeaax.polytechnique.fr/papers/theses/per.ps.gz ]
Keywords: evolution, genetic algorithms, temporal differences, GNU Go
[Ryd95]
Henrik Rydberg. GoLife I - a program that plays Go. Master's thesis, Chalmers University of Technology, Gothenburg, Sweden, 1995. [ http://web.comhem.se/~u70903172/Codes/Golife/golife.pdf ]
Keywords: quality function
[SOY+91]
Noriaki Sanechika, Hiroaki Oki, S. Yoshikawa, T. Yoshioka, and S. Uchida. “go generation” a Go playing system. Technical Report TR545, ICOT, Japan, 1991. [ http://www.icot.or.jp/ARCHIVE/Museum/TRTM/tr-list-E.html ]
[SOAS91]
Noriaki Sanechika, Hiroaki Oki, Takashi Akaosugi, and Shinichi Sei. Methodology of GOSEDAI. Technical Report TR717, ICOT, Japan, 1991. [ http://www.icot.or.jp/ARCHIVE/Museum/TRTM/tr-list-E.html ]
[San91]
Noriaki Sanechika. The specifications of ”Go generation”. Technical Report TR720, ICOT, Japan, 1991. [ http://www.icot.or.jp/ARCHIVE/Museum/TRTM/tr-list-E.html ]
[SGHM07]
Scott Sanner, Thore Graepel, Ralf Herbrich, and Tom Minka. Learning CRFs with hierarchical features: An application to Go. In Proceedings of the Workshop on Constrained Optimization and Structured Output Spaces (at ICML-07), 2007. [ http://www.cs.toronto.edu/~ssanner/Papers/crfgo.pdf ]
Keywords: grid-based conditional random fields, hierarchical pattern features, BMA-Tree algorithm
[SDS94]
Nicol N. Schraudolph, Peter Dayan, and Terrence J. Sejnowski. Temporal difference learning of position evaluation in the game of Go. In Advances in Neural Information Processing 6. Morgan Kaufmann, 1994. [ http://www.gatsby.ucl.ac.uk/~dayan/papers/sds94.pdf ]
Keywords: go, neural network, temporal difference learning, TD
[SDS00]
Nicol N. Schraudolph, Peter Dayan, and Terrence J. Sejnowski. Learning to Evaluate Go Positions via Temporal Difference Methods. Springer Verlag, Berlin, 2000. [ http://www.gatsby.ucl.ac.uk/~dayan/papers/sds00.pdf ]
Keywords: neural network, temporal difference learning
[SIT91]
Shinichi Sei, Nobuyuki Ichiyoshi, and Kazuo Taki. Experimental version of parallel computer Go-playing system GOG. Technical Report TR 669, ICOT, Japan, 1991. [ http://www.icot.or.jp/ARCHIVE/Museum/TRTM/tr-list-E.html ]
Keywords: GOG
[SOS+91]
Shinichi Sei, Hiroaki Oki, Noriaki Sanechika, Takashi Akaosugi, and Kazuo Taki. Experimental version of parallel computer Go-playing systems GOG. Technical Report TR718, ICOT, Japan, 1991. [ http://www.icot.or.jp/ARCHIVE/Museum/TRTM/tr-list-E.html ]
Keywords: GOG
[Sei98]
Shinichi Sei. Memory-based approach in Go-program KATSUNARI. In Ian Frank, Hitoshi Matsubara, Morihiko Tajima, Atsushi Yoshikawa, Reijer Grimbergen, and Martin Müller, editors, Complex Games Lab Workshop. Electrotechnical Laboratory, Machine Inference Group, Tsukuba, Japan, 1998. [ http://www.cs.ualberta.ca/~mmueller/cgo/cg98-workshop/Sei.pdf ]
Keywords: pattern, knowledge, KATSUNARI, joseki
[SK00]
Shinichi Sei and Toshiaki Kawashima. A solution of Go on 4x4 board by game tree search program. In 4th Game Informatics Group Meeting in IPS Japan, pages 69-76, 2000. In Japanese. English translation available. [ http://homepage1.nifty.com/Ike/katsunari/publications_e.html ]
Keywords: solving, solution, small boards
[Shi58]
Takuya Shimada. Problems In Composing Igo Rules. 1958. [ http://www.goban.demon.co.uk/go/shimada/chap6.html ]
Keywords: rules, dame, bent four in a corner
[Sie05]
Aaron Siegel. Loopy Games and Computation. PhD thesis, University of California, Berkeley, 2005. [ http://www.integraldomain.net/aaron/thesis/thesis.pdf ]
Keywords: combinatorial games theory, Go endgames, CGSuite Go Explorer
[SSM07]
David Silver, Richard Sutton, and Martin Müller. Reinforcement learning of local shape in the game of Go. In IJCAI 2007, 2007. [ http://www.cs.ualberta.ca/~mmueller/ps/silver-ijcai2007.pdf ]
Keywords: temporal difference learning
[KSS07]
Anna Koop, Richard Sutton, and David Silver. On the role of tracking in stationary environments. In ICML 2007, 2007. [ http://www.cs.ualberta.ca/~silver/research/publications/files/tracking.pdf ]
Keywords: tracking, temporal-difference, meta-learning, step-size adaptation
[Smi96]
Warren D. Smith. Hash functions for binary and ternary words. Technical report, NEC Research Institute, Princeton NJ, 1996. [ http://www.neci.nj.nec.com/homepages/wds/works.html ]
Keywords: hash function
[Smi04]
Chris Smith. A Computer-Go board evaluation function. Honors Thesis. Department of Computer Science at Trinity University, 2004. [ http://home.comcast.net/~logospathosethos/Honors_Thesis.doc ]
Keywords: Evaluation function
[Spi02]
Bill Spight. Analysis of the 4/21/98 Jiang-Rui endgame. In Richard Nowakowski, editor, More Games of No Chance, number 42 in Mathematical Sciences Research Institute Publications, pages 89-105. Mathematical Sciences Research Institute, Cambridge University Press, 2002. [ http://www.msri.org/communications/books/Book42/files/spight.pdf ]
Keywords: Thermographs
[SM04]
Kenneth O. Stanley and Risto Miikkulainen. Evolving a roving eye for Go. In Genetic and Evolutionary Computation - GECCO 2004, Part II, pages 1226-1238, 2004. [ http://www.cs.utexas.edu/users/nn/downloads/papers/stanley.gecco04.pdf ]
Keywords: Neural network, input field
[SGM04]
David Stern, Thore Graepel, and David J.C. MacKay. Modelling uncertainty in the game of Go. In Advances in Neural Information Processing Systems 17, 2004. [ http://www.inference.phy.cam.ac.uk/dhs26/publications/nips2004.ps.gz ]
Keywords: uncertainty, probability, Markov random field, learning
[SHG07]
David Stern, Ralf Herbrich, and Thore Graepel. Learning to solve game trees. In ICML 2007, 2007. [ http://www.machinelearning.org/proceedings/icml2007/papers/394.pdf ]
Keywords: probability distributions, game tree search, graphical model
[Sto91]
David Stoutamire. Machine Learning, Game Play, and Go. PhD thesis, Case Western Reserve University, 1991. [ http://david.stoutamire.com/caisr_report.ps ]
Keywords: Learning, error function, hash, patterns
[JS03]
H. Blockeel J. Struyf, J. Ramon. Compact representation of knowledge bases in ILP. In S. Matwin and C. Sammut, editors, Inductive Logic Programming, 12th International Conference, ILP 2002, volume 2583 of Lecture Notes in Computer Science, pages 254-269, 2003. [ http://www.cs.kuleuven.ac.be/~dtai/publications/files/38663.ps.gz ]
[Taa94]
Niels A. Taatgen. The study of learning mechanisms in unified theories of cognition. Lisse, the Netherlands: Swets & Zeitlinger, 1994. [ http://tcw2.ppsw.rug.nl/~niels/publications/cip.ps ]
Keywords: cognition, psychology, UTC, Soar
[Tak01]
Takenobu Takizawa. An Application of Mathematical Game Theory to Go Endgames: Some Width-Two-Entrance Rooms With and Without Kos, pages 107-124. Cambridge University Press, 2001. [ http://msri.org/publications/books/Book42/files/takizawa.pdf ]
Keywords: endgame, combinatorial game theory, width-two-entrance rooms
[Tal97]
David Talby. Revising partition search to play Go. Technical report, Hebrew University of Jerusalem, 1997. [ http://www.cs.huji.ac.il/~davidt/done/go/index.html ]
Keywords: Partition search,
[Tav02]
Wouter Tavernier. De intelligentie van de toekomst: een praktische en filosofische reflectie over de grenzen en de toekomst van de machine. Master's thesis, Universiteit Gent, 2002. In Dutch. [ http://studwww.rug.ac.be/~wtaverni/thesis.htm ]
[Tay04]
Choon Tay. Solving Go on a 3x3 board using temporal-difference learning. Technical report, University of Western Australia, 2004. Supervisor Cara MacNish. [ http://undergraduate.csse.uwa.edu.au/year4/Current/Students/Files/2004/ChoonTay/CorrectedDissertation.pdf ]
Keywords: TD-learning
[Tho00]
Thomas Thomsen. Lambda-search in game trees - with application to Go, pages 19-38. Volume 2063 of Jaap and Iida [JI00], October 2000. [ http://www.t-t.dk/publications/index.html ]
Keywords: Binary tree search, threat-sequences, null-moves, proof-number search, abstract game-knowledge, Go block tactics, lambda-search
[TF06]
John Tromp and Gunnar Farnebäck. Combinatorics of Go. Submitted to CG 2006, 2006. [ http://homepages.cwi.nl/~tromp/go/gostate.ps ]
Keywords: Number of legal positions, number of games, dynamic programming, game tree complexity, base of liberties
[Upt98]
Robin Upton. Dynamic Stochastic Control: A New Approach to Tree Search & Game-Playing. PhD thesis, University of Warwick, UK, 1998. [ http://www.robinupton.com/research/phd/Game_Tree_Searching_with_DSC_(Upton,1998).pdf ]
Keywords: game tree search, selective search, markov chain model, dynamic stochastic control, PCN*
[Urv02]
Tanguy Urvoy. Pattern matching in Go with DFA, 2002. [ http://tanguy.urvoy.free.fr/Papers/dfabstract.pdf ]
Keywords: Fast pattern matcher, Deterministic Finite State Automata
[VVD04]
L. Veenstra, A. Venghaus, and P. Drake. Pattern matching in the game of Go. Poster to be presented at the Thirteenth Regional Conference on Undergraduate Research, Murdock College Research Program at Lewis & Clark College, 2004. [ https://webdisk.lclark.edu/xythoswfs/webui/_xy-13651_1-tid_jDVKYDTf ]
[Ver02]
Tijs Vermeulen. Computergo alternatieve technieken. Master's thesis, Universiteit Gent, 2002. In Dutch. [ http://users.pandora.be/tijs.vermeulen/ ]
[VC03]
R. Vila and T. Cazenave. When one eye is sufficient. In Advance in Computer Games 10. Kluwer, 2003. [ http://www.ai.univ-paris8.fr/~cazenave/eyeLabelling.pdf ]
Keywords: eye, neighbour classification, life property
[Wan04]
Harry Wang. A temporal model with influence and territory in computer go. Technical report, University of California, Santa Cruz, May 2004. [ http://sluggo.dforge.cse.ucsc.edu/harryMS.pdf ]
Keywords: SlugGo, GNU Go, MPI, Influence, Territory
[Wan05]
Kai Wang. Improving sluggo through hashing and sub-branching. Master's thesis, University of California, Santa Cruz, June 2005. [ http://sluggo.dforge.cse.ucsc.edu/kaiMS.pdf ]
Keywords: SlugGo, GNU Go
[vdWvdH01]
Erik van der Werf and Jaap van den Herik. Visual learning in Go. In The CMG 6th Computer Olympiad Computer-Games Workshop Proceedings, 2001. [ http://www.cs.unimaas.nl/~vanderwerf/publications.html ]
Keywords: Learning, Eye-based recurrent network architechture, ERNA, neural network
[vdWUPvdH02]
Erik van der Werf, Jos Uiterwijk, Eric Postma, and Jaap van den Herik. Local move prediction in Go. In 3rd International Conference on Computers and Games, Edmonton, 2002. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/lmp_cg02.ps.gz ]
Keywords: expert moves, learning, feature extraction, move pair analysis, modified eigenspace separation, transform, move prediction
[vdWUvdH02]
Erik van der Werf, Jos Uiterwijk, and Jaap van den Herik. Solving Ponnuki-Go on small boards. In 7th Computer Olympiad Computer-Games Workshop Proceedings, Maastricht, July 2002. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/ponnuki_olympiad02.ps.gz ]
Keywords: Ponnuki Go, Atari Go, capture Go, evaluation function, search enhancements
[vdWvdHU03]
Erik van der Werf, Jaap van den Herik, and Jos Uiterwijk. Solving Go on small boards. ICGA Journal, 26(2):92-107, 2003. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/solving_go_on_small_boards.ps.gz ]
Keywords: solving, alpha-beta, GHI, 5x5, Migos
[EvdW03]
J.W.H.M. Uiterwijk E.C.D. van der Werf, H.J. van den Herik. Learning to score final positions in the game of Go. In 10th Advances in Computer Games conference, pages 143-158, 2003. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/learning_to_score.pdf ]
Keywords: learning, neural net, scoring, game records, life and death
[EvdWvdHU03]
M.H.M. Winands E.C.D. van der Werf, H.J. van den Herik, and J.W.H.M. Uiterwijk. Learning to predict life and death from Go game records. In Ken Chen et al., editor, Proceedings of JCIS 2003 7th Joint Conference on Information Sciences, pages 501-504, Research Triangle Park, North Carolina, USA, 2003. JCIS/Association for Intelligent Machinery. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/lld_jcis03.pdf ]
[EvdW04]
J. W. H. M. Uiterwijk E.C.D. van der Werf, H.J. van den Herik. Learning to estimate potential territory in the game of Go. In 4th International Conference on Computers and Games (CG'04), 2004. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/predicting_territory.pdf ]
[vdW04]
E.C.D. van der Werf. AI techniques for the game of Go. PhD thesis, Universiteit Maastricht, Maastricht, The Netherlands, 2004. [ http://www.cs.unimaas.nl/~vanderwerf/pubdown/thesis_erikvanderwerf.ps.gz ]
[Wil95]
Bruce Wilcox. RiscIgo design, 1995. Computer Go Mailing List.
Keywords: RiscIgo
[Wil97]
Steven Willmott. Adversarial planning techniques and the game of Go. Master's thesis, Departement of Artificial Intelligence, University of Edinburgh, 1997. [ http://www.lsi.upc.es/~steve/Edinburgh/snw.ps.gz ]
Keywords: adversarial
[WBLR98b]
Steven Willmott, Alan Bundy, John Levine, and Julian Richardson. Adversarial planning in complex domains. Technical Report 889, Department of Artificial Intelligence, University of Edinburgh, January 1998. [ http://www.dai.ed.ac.uk/pub/daidb/papers/rp889.ps.gz ]
Keywords: adversarial, co-operative, agent
[WBLR98a]
Steven Willmott, Alan Bundy, John Levine, and Julian Richardson. An adversarial planning approach to Go. In Jaap and Iida [JI98], pages 93-112. [ http://ase.arc.nasa.gov/people/julianr/www/publications/gobi_llncs.ps ]
Keywords: planning
[WBLR99]
Steven Willmott, Alan Bundy, John Levine, and Julian Richardson. Applying adversarial planning techniques to Go. Journal of Theoretical Computer Science, March 1999. [ http://dream.dai.ed.ac.uk/publications/98-03/willmott99.ps.gz ]
Keywords: adversarial planning, planning
[Wol92]
Thomas Wolf. Tsume go with RisiKo. In Game Festival in Cannes/France, 1992. [ http://citeseer.ist.psu.edu/wolf92tsume.html ]
Keywords: tsume go, life and death
[Wol93]
Thomas Wolf. Quality improvements in the tsume go mass production. In Proceedings of the Game Festival in Cannes/France, 1993, 1993. [ http://citeseer.ist.psu.edu/wolf93quality.html ]
Keywords: tsume go, life and death
[Wol94]
Thomas Wolf. The program Gotools and its computer-generated tsume go database. In 1st Game Programming Workshop in Japan, Hakone, 1994, 1994. [ http://www.qmw.ac.uk/~ugah006/gotools/hakone94.ps ]
Keywords: tsume go, life and death, database
[Wol96a]
Thomas Wolf. About problems in generalizing a tsumego program to open positions. In 3rd Game Programming Workshop in Japan, Hakone, 1996, 1996. [ http://www.qmw.ac.uk/~ugah006/gotools/hakone96.ps ]
Keywords: tsume go, life and death, open position
[Wol97a]
Thomas Wolf. About computer go and the tsume go program Gotools, 1997. Based on an article from 1st game programming workshop, hakone, Japan, 1994. [ http://citeseer.ist.psu.edu/wolf97about.html ]
Keywords: tsume go, life and death
[Wol97b]
Thomas Wolf. The diamond. British Go Journal, Autumn 1997, 1997. [ http://alpha.qmw.ac.uk/~ugah006/gotools/diamond/diamond.ps ]
Keywords: tsume go
[Wol00]
Thomas Wolf. Forward pruning and other heuristic search technics in tsume go. Information Sciences, 122(1):59-76, 2000. [ http://lie.math.brocku.ca/twolf/papers/jis_nat.ps ]
Keywords: GoTools, tsume go, life and death, forward pruning, heuristic
[PW03]
Matthew Pratola and Thomas Wolf. Optimizing GoTools' search heuristics using genetic algorithms. ICGA Journal, 26(1):28-49, 2003. [ http://lie.math.brocku.ca/twolf/papers/ga-report.ps ]
Keywords: GoTools, Life and Death, TsumeGo, Genetic Algorithms, Open Boundary
[Wol06]
Thomas Wolf. A library of eyes in Go, I: Life & death definition consistent with `bent-4'. Preprint, accepted for publication in the proceedings of the International Workshop on Combinatorial Game theory at BIRS (Banff International Research Station), 2006. [ http://lie.math.brocku.ca/twolf/papers/bent4.pdf ]
Keywords: life and death, ko, bent-4-in-the-corner, eye-library
[WP06]
Thomas Wolf and Matthew Pratola. A library of eyes in Go, II: Monolithic eyes. Preprint, accepted for publication in the proceedings of the International Workshop on Combinatorial Game theory at BIRS (Banff International Research Station), 2006. [ http://lie.math.brocku.ca/twolf/papers/mono.pdf ]
Keywords: life and death, ko, eye-library, monolithic, GoTools
[WS07a]
Thomas Wolf and Lei Shen. Checking life & death problems in Go I: The program ScanLD. Preprint, 2007. [ http://lie.math.brocku.ca/twolf/papers/bugsintro.ps ]
Keywords: life and death, solution checker
[WS07b]
Thomas Wolf and Lei Shen. Checking life & death problems in Go II: Results. Preprint, 2007. [ http://lie.math.brocku.ca/twolf/papers/bugsextra.ps ]
Keywords: life and death, solution checker
[Wol07]
Thomas Wolf. Two applications of a life & death problem solver in Go. Preprint, submitted to Journal of ÖGAI, special issue for the European Go Championship in Vienna 2007, 2007. [ http://lie.math.brocku.ca/twolf/papers/over.ps ]
Keywords: life and death, solution checker, single eyes, database
[WE94]
David Wolfe and Berlekamp Elwyn. Mathematical Go, 1994. Talk slides. [ http://www.gac.edu/~wolfe/papers/ ]
Keywords: combinatorial game theory
[Wol96b]
David Wolfe. The Gamesman's Toolkit, pages 93-98. Cambridge University Press, 1996. [ http://www.msri.org/publications/books/Book29/files/wolfe.pdf ]
Keywords: go, program, calculate, UNIX, C, combinatorial
[Wol99]
David Wolfe. Go endgames are PSPACE-hard, 1999. Submitted to Theoretical Computer Science. [ http://www.gac.edu/~wolfe/papers/ ]
Keywords: Go, PSPACE, endgames, games
[WB07]
Lin Wu and Pierre Baldi. A scalable machine learning approach to Go. In B. Schölkopf, J. Platt, and T. Hoffman, editors, Advances in Neural Information Processing Systems 19, pages 1521-1528. MIT Press, Cambridge, MA, 2007. [ http://books.nips.cc/papers/files/nips19/NIPS2006_0223.pdf ]
Keywords: evaluation function, neural network
[Yed85]
Laura Yedwab. On playing well in a sum of games. Master's thesis, Massachusetts Institute of Technology, 1985. [ http://www.lcs.mit.edu/publications/pubs/pdf/MIT-LCS-TR-348.pdf ]
Keywords: sum of games, computational complexity, approximate solutions, optimal search strategies
[YCH98]
Shi-Jim Yen, Wen-Jyh Chen, and Shun-Chin Hsu. Design and implementation of a heuristic beginning system for computer Go. In JCIS 1998, pages 381-384. Association for Intelligent Machinery, 1998. [ http://www.csie.ndhu.edu.tw/~sjyen/Papers/1998OpenGame.pdf ]
Keywords: beginning game, opening, Joseki, Moyo, Jimmy
[YH01]
Shi-Jim Yen and Shun-Chin Hsu. A positional-judgement system for computer Go. In Advances in Computer Games, volume 9, pages 313-326. Universiteit Maastricht, 2001. [ http://www.csie.ndhu.edu.tw/~sjyen/Papers/2001PJ.pdf ]
Keywords: positional judgment, Jimmy
[YYH02]
Shi-Jim Yen, JC Yen, and Shun-Chin Hsu. Move strategies in middle game of computer Go. In 7th TAAI, Taiwan, 2002. In Chinese. [ http://www.csie.ndhu.edu.tw/~sjyen/Papers/2002MidGame.pdf ]
[Yos98]
Hiroto Yoshii. Move evaluation tree system. In Ian Frank, Hitoshi Matsubara, Morihiko Tajima, Atsushi Yoshikawa, Reijer Grimbergen, and Martin Müller, editors, Complex Games Lab Workshop. Electrotechnical Laboratory, Machine Inference Group, Tsukuba, Japan, 1998. [ http://www.cs.ualberta.ca/~mmueller/cgo/cg98-workshop/Yoshii.pdf ]
Keywords: move evaluation tree system, METS, emergency value, database
[YKM07]
Kazuki Yoshizoe, Akihiro Kishimoto, , and Martin Müller. Lambda depth-first proof number search and its application to Go. In IJCAI 2007, 2007. [ http://www.cs.ualberta.ca/~mmueller/ps/yoshizoe.pdf ]
Keywords: LDFPN, DFPN, lambda search
[ZPW97]
Raonak Zaman, Danil Prokhorov, and Donald C. Wunsch. Adaptive critic design in learning to play game of Go. Technical report, Texas Tech University, Lubbock, 1997. [ http://www.ece.umr.edu/acil/Publications/CONFERENCE/Adaptive_critic_design_in.pdf ]
Keywords: ACD, adaptive critic, learning, TD, temporal difference learning
[ZW99]
Raonak Zaman and Donald C. Wunsch. TD methods applied to mixture of experts for learning 9x9 Go evaluation function, 1999. [ http://www.ece.umr.edu/acil/Publications/CONFERENCE/TD methods applied.pdf ]
Keywords: TD, temporal difference learning, neural networks, Meta-Pi, mixture of experts
[Zha04]
Xiaoyu Zhang. Parallel computing as a way to go. Master's thesis, University of California, Santa Cruz, September 2004. [ http://sluggo.dforge.cse.ucsc.edu/willMS.pdf ]
Keywords: SlugGo, GNU Go
[ZM05]
Ling Zhao and Martin Müller. Solving probabilistic combinatorial games. In 11th Advances in Computer Games Conference, 2005. [ http://www.cs.ualberta.ca/~mmueller/ps/solvepm.pdf ]
Keywords: PCG, probability distribution, local evaluation, Monte-Carlo

This file has been generated by bibtex2html 1.88.