Go - Chess Programming Wiki

19*19 Go board 1 1919 Go board ¹*

The Age of Intelligent Machines ↩︎

The game of Go has attracted game researchers and programmers as an ambitious AI-challenge. Albert Zobrist was a pioneer, who wrote the first Go program in 1968 as part of his Ph.D. Thesis on pattern recognition ¹. Chess programmers, beside others, Rémi Coulom and Gian-Carlo Pascutto became successful Go programmers with their programs CrazyStone and Leela respectively. Competitive computer Go, as organized by the ICGA ², is played on boards with 9x9 as well with default 19x19 grids. Since Go lacks a simple evaluation function mainly based on counting material, attempts to apply similar techniques and algorithms as in chess were less successful. The breakthrough in computer Go was accomplished by Monte-Carlo tree search and deep learning.

Contents

Progress

Monte-Carlo Go

After early trials to apply Monte Carlo methods to a Go playing program by Bernd Brügmann in 1993 ³, recent developments since the mid 2000s by Bruno Bouzy ⁴, and by Rémi Coulom, who coined the term Monte-Carlo Tree Search ⁵, in conjunction with UCT (Upper Confidence bounds applied to Trees) introduced by Levente Kocsis and Csaba Szepesvári ⁶, led to a breakthrough in computer Go ⁷.

CNNs

As mentioned by Ilya Sutskever and Vinod Nair in 2008 ⁸, convolutional neural networks are well suited for problems with a natural translation invariance, such as object recognition. Go has some translation invariance, because if all the pieces on a hypothetical Go board are shifted to the left, then the best move will also shift (with the exception of pieces that are on the boundary of the board). Many applications of neural networks to Go have already used convolutional neural networks, such as Nicol N. Schraudolph et al. ⁹, Erik van der Werf et al. ¹⁰, and Markus Enzenberger ¹¹, among others.

In 2014, two teams independently investigated whether deep convolutional neural networks ¹² could be used to directly represent and learn a move evaluation function for the game of Go. Christopher Clark and Amos Storkey trained an 8-layer convolutional neural network by supervised learning from a database of human professional games, which without any search, defeated the traditional search program Gnu Go in 86% of the games ¹³ ¹⁴ ¹⁵ ¹⁶ ¹⁷. In their paper Move Evaluation in Go Using Deep Convolutional Neural Networks ¹⁸, Chris J. Maddison, Aja Huang, Ilya Sutskever, and David Silver report they trained a large 12-layer convolutional neural network in a similar way, to beat Gnu Go in 97% of the games, and matched the performance of a state-of-the-art Monte-Carlo Tree Search that simulates a million positions per move ¹⁹.

AlphaGo

In 2015, a team affiliated with Google DeepMind around David Silver, Aja Huang, Chris J. Maddison, and Demis Hassabis, supported by Google researchers John Nham and Ilya Sutskever, build a Go playing program dubbed AlphaGo, combining Monte-Carlo tree search with their 12-layer networks ²⁰, the “policy network,” to select the next move, the “value network,” to predict the winner of the game. The neural networks were trained on 30 million moves from games played by human experts, until it could predict the human move 57 percent of the time. AlphaGo achieved a huge winning rate against other Go programs, and defeated European Go champion Fan Hui ²¹ in October 2015 with a 5 - 0 score ²² On March 9 to 15, 2016, AlphaGo won a $1M 5-game challenge match in Seoul versus Lee Sedol with 4 - 1 ²³ ²⁴ ²⁵. During The Future of Go Summit from May 23 to 27, 2017 in Wuzhen, China, AlphaGo won a three-game match versus current world No. 1 ranking player Ke Ji. After the Summit, AlphaGo is now retired from competitive play while DeepMind continues AI research in other areas ²⁶.

AlphaGo Zero & AlphaZero

However, in October 2017, AlphaGo Zero, an evolution of AlphaGo was introduced. While previous versions were initially trained on thousands of human amateur and professional games to learn how to play Go, AlphaGo Zero learns exclusively by playing games against itself, starting from completely random play, to quickly surpass human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0 ²⁷ ²⁸. AlphaGo Zero was further improved and even generalized for other games now dubbed AlphaZero, as published in December 2017 ²⁹.

Fine Art

Fine Art is a Go playing entity developed since 2016 under the patronage of the Chinese media company Tencent by a team around Liu Yongsheng, along with Ma Bo, Tang Shanmin, Wu Guangyu, and Zhang Kaixu. It won the Computer Go UEC Cup at the University of Electro-Communications, Chōfu, Tokyo, Japan, in March 2017 against a field of 27 other programs including DeepZenGo and Crazy Stone ³⁰. In January 2018, it defeated Ke Jie 9P in 77 moves after giving two stones handicap ³¹ on Fox Weiqi ³² server ³³.

Quotes

Quote by Gian-Carlo Pascutto in 2010 ³⁴:

There is no significant difference between an alpha-beta search with heavy LMR and a static evaluator (current state of the art in chess) and an UCT searcher with a small exploration constant that does playouts (state of the art in go).

The shape of the tree they search is very similar. The main breakthrough in Go the last few years was how to backup an uncertain Monte Carlo score. This was solved. For chess this same problem was solved around the time quiescent search was developed.

Both are producing strong programs and we've proven for both the methods that they scale in strength as hardware speed goes up.

So I would say that we've successfully adopted the simple, brute force methods for chess to Go and they already work without increases in computer speed. The increases will make them progressively stronger though, and with further software tweaks they will eventually surpass humans.

Computer Olympiads

Selected Publications

³⁵

1960 ...

Jack Good (1965). The Mystery of Go. Literature: Reports hosted by Atlas Computer Laboratory

1970 ...

Albert Zobrist (1970). Feature Extraction and Representation for Pattern Recognition and the Game of Go. Ph.D. Thesis (152 pp.), University of Wisconsin, also published as technical report, pdf
Walter R. Reitman, James Kerwin, Robert Nado, Judith S. Reitman, Bruce Wilcox (1974). Goals and Plans in a Program for Playing Go. Proceedings of the 29th ACM Conference, reprinted in David Levy (ed.) (1988). Computer Games II. google books
Walter R. Reitman, Bruce Wilcox (1975). Perception and representation of spatial relations in a program for playing Go. Proceedings of the 30th ACM Conference, reprinted in David Levy (ed.) (1988). Computer Games II.
David B. Benson (1976). Life in the Game of Go. Information Sciences, Vol. 10, pdf
Judith S. Reitman (1976). Skilled Perception in Go: Deducing Memory Structures from Inter-Response Times. Cognitive Psychology, Vol. 8, No, 3
Walter R. Reitman, Bruce Wilcox (1977). Pattern Recognition and Pattern-Directed Inference in a Program for Playing Go. ACM SIGART Bulletin, No. 63, reprinted in David Levy (ed.) (1988). Computer Games II.
Editor (1979). Computer GO Has Come. Personal Computing, Vol. 3, No. 5, pp. 55
Walter R. Reitman, Bruce Wilcox (1979). Modelling Tactical Analysis and Problem Solving in Go. Proceedings of the Tenth Annual Pittsburgh Conference on Modelling and Simulation
Walter R. Reitman, Bruce Wilcox (1979). The Structure and Performance of the INTERIM.2 Go Program. IJCAI 1979, reprinted in David Levy (ed.) (1988). Computer Games II.

1980 ...

Editor (1980). The Challenge of Computer Go. Personal Computing, Vol. 4, No. 8, pp. 79
Editor (1980). Zobrist Program in Action. Personal Computing, Vol. 4, No. 8, pp. 81 » Albert Zobrist
Bruce Wilcox (1985). Reflections on building two Go programs. ACM SIGART Bulletin, No. 94
Anders Kierulf (1985). Smart Go Board: Algorithms for the Tactical Calculator. Diploma thesis (unpublished), ETH Zurich.
David Levy (ed.) (1988). Computer Games II. Springer, ISBN: 978-1-4613-8756-5, Chapter 5 - Go
Janusz Kraszek (1988). Heuristics in the life and death algorithm of a Go playing program. Computer Go 9 (Winter 1988-89)
Anders Kierulf, Jürg Nievergelt (1989). Swiss Explorer blunders its way into winning the first computer Go Olympiad. Heuristic Programming in AI 1
Ken Chen (1989). Group Identification in Computer Go. Heuristic Programming in AI 1

1990

Ken Chen (1990). The Move Decision Process of Go Intellect, Computer Go, No.14, pp. 9-17.
Ken Chen, Anders Kierulf, Martin Müller, Jürg Nievergelt (1990). The Design and Evolution of Go Explorer. Computers, Chess, and Cognition
Kiyoshi Shirayanagi (1990). Knowledge Representation and its Refinement in Go Programs. Computers, Chess, and Cognition

1991

David Wolfe (1991). Mathematics of Go: Chilling Corridors. Ph.D. thesis, University of California, Berkeley, advisor Elwyn Berlekamp
Herbert D. Enderton (1991). The Golem Go Program. Technical Report CMU-CS-92-101, Carnegie Mellon University
Ken Chen (1991). Go Intellect wins two Gold Medals. Heuristic Programming in AI 2
Barney Pell (1991). Exploratory Learning in the Game of GO. Heuristic Programming in AI 2
Thomas Wolf (1991). Investigating Tsumego Problems with "RisiKo". Heuristic Programming in AI 2

1992

Warren D. Smith (1992). Hash functions for Binary and Ternary Words. NEC Research Institute, ps
Thomas Wolf (1992). Generating tsume go problems with GoTools. Heuristic Programming in AI 4 ³⁶

1993

David Fotland (1993). Knowledge representation in the Many Faces of Go.
Bernd Brügmann (1993). Monte Carlo Go. pdf ³⁷
Nicol N. Schraudolph, Peter Dayan, Terrence J. Sejnowski (1993). Temporal Difference Learning of Position Evaluation in the Game of Go. NIPS 1993 ³⁸

1994

Elwyn Berlekamp, David Wolfe (1994). Mathematical Go - Chilling Gets the Last Point. [https://en.wikipedia.org/wiki/A_K_Peters,_Ltd. A K Peters Ltd.], also in paperback as Mathematical Go Endgames: Nightmares For the Professional Go Player. Ishi Press ³⁹

1995 ...

Jay Burmeister, Janet Wiles (1995). CS-TR-339 Computer Go Tech Report. Departments of Computer Science and Psychology, The University of Queensland, QLD 4072, Australia (permanently - under construction)
Jay Burmeister, Janet Wiles (1995). The Challenge of Go as a Domain for AI Research: A Comparison Between Go and Chess. In Proceedings of the Third Australian and New Zealand Conference on Intelligent Information Systems, IEEE Western Australia Section, pdf
Tristan Cazenave (1995). Learning and Problem Solving in Gogol, a Go playing program. pdf

1996

Bruce Wilcox, Sue Wilcox (1996). EZ-GO-Oriental Strategy in a Nutshell. KI Press, ISBN13 978-0965223546 ⁴⁰
Markus Enzenberger (1996). The Integration of A Priori Knowledge into a Go Playing Neural Network.
Martin Müller, Ralph Gasser (1996). Experiments in Computer Go Endgames. Games of No Chance edited by Richard J. Nowakowski
Martin Müller, Elwyn Berlekamp, Bill Spight (1996). Generalized thermography: Algorithms, implementation, and application to Go endgames. Technical Report 96-030, ICSI Berkeley, 1996. postscript
Bruno Bouzy, Tristan Cazenave (1996). Shared concepts between complex systems and the game of Go. pdf

1997

Tristan Cazenave (1997). Gogol (an Analytical Learning Program). IJCAI'97, pdf
Bruno Bouzy, Tristan Cazenave (1997). Using the Object Oriented Paradigm to Model Context in Computer Go. Context'97, pdf
David Fotland, Atsushi Yoshikawa (1997). The 3rd Fost-Cup World-Open Computer-Go Championship. ICGA Journal, Vol. 20, No. 4

1998

Ken Chen (1998). Heuristic Search in Go Game Tree, Proceedings of Joint Conference on Information Sciences ’98, Vol. II, pp. 274-278. The Association for Intelligent Machinery, Inc. ISBN 0-9643456-7-6.
Tristan Cazenave (1998). Integration of Different Reasoning Modes in a Go Playing and Learning System. pdf
Bill Spight (1998). Extended Thermography for Multiple Kos in Go. CG 1998
Martin Müller (1998). Computer Go: A Research Agenda. CG 1998
Shinichi Sei, Toshiaki Kawashima (1998). Memory-Based Approach in Go-program KATSUNARI. Fujitsu Social Science Laboratory, pdf
Morihiko Tajima, Noriaki Sanechika (1998). Estimating the Possible Omission Number for Groups in Go by the Number of n -th Dame. CG 1998
Norman Richards, David E. Moriarty, Risto Miikkulainen (1998). Evolving Neural Networks to Play Go. Applied Intelligence, Vol. 8, No. 1

1999

Ken Chen, Zhixing Chen (1999). Static Analysis of Life and Death in the Game of Go. Information Sciences, Vol. 121, Nos. 1-2, pdf

2000 ...

Thomas Thomsen (2000). Lambda-Search in Game Trees - with Application to Go. CG 2000 also published in ICGA Journal, Vol. 23, No. 4, winning the 2001 ICGA Journal Award, preprint as pdf » Lambda-Search
Jan Ramon, Tom Francis, Hendrik Blockeel (2000). Learning a Go Heuristic with Tilde. CG 2000
Martin Müller (2000). Review: Computer Go 1984–2000. CG 2000
Jay Burmeister (2000). Studies in Human and Computer Go: Assessing the Game of Go as a Research Domain for Cognitive Science. Ph.D. thesis, School of Computer Science and Electrical Engineering and School of Psychology, The University of Queensland, Australia, pdf
Jay Burmeister, Yasuki Saito, Atsushi Yoshikawa, Janet Wiles (2000) Memory Performance of Master Go Players. in Jaap van den Herik, Hiroyuki Iida (eds.) (2000). Games in AI Research. pp. 271-286
Ken Chen (2000). Some Practical Techniques for Global Search in Go. ICGA Journal, Vol. 23, No. 2
Kuo-Yuan Kao (2000). Mean and Temperature Search for Go Endgames. Information Sciences, Vol. 122, No. 1
Marcel Crâsmaru, John Tromp (2000). Ladders Are PSPACE-Complete. CG 2000
Shinichi Sei, Toshiaki Kawashima (2000). A Solution of Go on 4x4 Board by Game Tree Search Program. Fujitsu Social Science Laboratory, Japanese pdf
Thomas Wolf (2000). Forward Pruning and Other Heuristic Search Techniques in Tsume Go. Special Issue of Information Sciences, Vol. 122, No. 1, CiteSeerX

2001

Bruno Bouzy (2001). Go Patterns Generated by Retrograde Analysis. 6th Computer Olympiad Workshop, pdf
Erik van der Werf, Jaap van den Herik (2001). Visual Learning in Go. 6th Computer Olympiad Workshop, pdf
Nicol N. Schraudolph, Peter Dayan, Terrence J. Sejnowski (2001). Learning to Evaluate Go Positions via Temporal Difference Methods. Computational Intelligence in Games, Studies in Fuzziness and Soft Computing, Physica-Verlag, revised version of 1993 paper
Tristan Cazenave (2001). Generating Patterns with External Conditions for the Game of Go. Advances in Computer Games 9, pdf
Jeng-Chi Yan, Shun-Chin Hsu (2001). A Positional Judgment System for computer Go. Advances in Computer Games 9
Bruno Bouzy, Tristan Cazenave (2001). Computer Go: an AI-oriented Survey. Artificial Intelligence Journal, Vol. 132, pdf
Alex B. Meijer, Henk Koppelaar (2001). A learning architecture for the game of Go. Game-On 2001
Alex B. Meijer, Henk Koppelaar (2001). Pursuing abstract goals in the game of Go. BNAIC 2001
Ken Chen (2001). Computer Go: Knowledge, Search, and Move Decision. ICGA Journal, Vol. 24, No. 4, pdf

2002

Tristan Cazenave (2002). Admissible Moves in Two-Player Games. SARA 2002, pdf
Ken Chen (2002). GO4++ wins 19x19 Go tournament. ICGA Journal, Vol. 25, No. 3 » 7th Computer Olympiad
Erik van der Werf (2002). GO4++ wins 9x9 Go tournament. ICGA Journal, Vol. 25, No. 3 » 7th Computer Olympiad
Erik van der Werf (2002). Solving Ponnuki-Go on Small Boards. 7th Computer Olympiad Workshop
Erik van der Werf, Jos Uiterwijk, Jaap van den Herik (2002). Solving Ponnuki-Go on Small Boards. BNAIC’02, pdf
Bruno Bouzy (2002). A Small Go Board Study of Metric and Dimensional Evaluation Functions. CG 2002
Erik van der Werf, Jos Uiterwijk, Eric Postma, Jaap van den Herik (2002). Local Move Prediction in Go. CG 2002
Bill Spight (2002). Evaluating Kos in a Neutral Threat Environment: Preliminary Results. CG 2002
Teigo Nakamura, Elwyn Berlekamp (2002). Analysis of Composite Corridors. CG 2002
David Fotland (2002). Static Eye in "The Many Faces of Go". ICGA Journal, Vol. 25, No. 4
Zhixing Chen (2002). Semi-Empirical Quantitative Theory of Go Part I: Estimation of the Influence of a Wall. ICGA Journal, Vol. 25, No. 4
Martin Müller (2002). Position Evaluation in Computer Go. ICGA Journal, Vol. 25, No. 4
David Wolfe (2002). Go endgames are PSPACE-hard. in Richard J. Nowakowski (ed) (2002). More Games of No Chance. Cambridge University Press

2003

Matthew Pratola, Thomas Wolf (2003). Optimizing GOTOOLS' Search Heuristics using Genetic Algorithms. ICGA Journal, Vol. 26, No. 1, also arXiv:cs/0302002 » Genetic Programming
Ken Chen (2003). Soft decomposition search and binary game forest model for move decision in Go, Information Sciences, Vol. 154, Issues 3-4, 157-172, pdf
Markus Enzenberger (2003). Evaluation in Go by a Neural Network using Soft Segmentation. Advances in Computer Games 10, pdf
Akihiro Kishimoto, Martin Müller. (2003). Df-pn in Go: An Application to the One-Eye Problem. Advances in Computer Games 10, pdf » Proof-Number Search ⁴¹
Erik van der Werf, Jaap van den Herik, Jos Uiterwijk (2003). Learning to Score Final Positions in the Game of Go. Advances in Computer Games 10, pdf
Bruno Bouzy, Bernard Helmstetter (2003). Monte Carlo Go Developments. Advances in Computer Games 10, pdf
Bruno Bouzy (2003). Mathematical morphology applied to computer go. IJPRAI Vol. 17, No. 2
Bruno Bouzy (2003). The move decision strategy of Indigo. ICGA Journal, Vol. 26, No. 1
Ken Chen (2003). The Way to Go is Bottom Up. ICGA Journal, Vol. 26, No. 2
Erik van der Werf, Jaap van den Herik, Jos Uiterwijk (2003). Solving Go on Small Boards. ICGA Journal, Vol. 26, No. 2, pdf
Ken Chen (2003). GNUGo wins 19x19 Go tournament. ICGA Journal, Vol. 26, No. 4 » 8th Computer Olympiad
Erik van der Werf (2003). Aya wins 9x9 Go tournament. ICGA Journal, Vol. 26, No. 4 » 8th Computer Olympiad
Alex B. Meijer, Henk Koppelaar (2003). Towards Multi-Objective Game Theory - with Application to Go. Game-On 2003, pdf

2004

Bruno Bouzy (2004). Associating Shallow and Selective Global Tree Search with Monte Carlo for 9 × 9 Go. CG 2004
Erik van der Werf, Jaap van den Herik, Jos Uiterwijk (2004). Learning to Estimate Potential Territory in the Game of Go. CG 2004, pdf
Xiaozhen Niu, Martin Müller (2004). An Improved Safety Solver for Computer Go. CG 2004
Jan Ramon, Tom Croonenborghs (2004). Searching for Compound Goals Using Relevancy Zones in the Game of Go. CG 2004
David Fotland (2004). Go Intellect wins 19x19 Go tournament. ICGA Journal, Vol. 27, No. 3 » 9th Computer Olympiad
Bruno Bouzy (2004). Go Intellect wins 9x9 Go tournament. ICGA Journal, Vol. 27, No. 3 » 9th Computer Olympiad
Erik van der Werf (2004). AI techniques for the game of Go. Ph.D. thesis, Universiteit Maastricht, Maastricht, The Netherlands. ISBN 90 5278 445 0, pdf
Bruno Bouzy (2004). Toward a go player computational model. Habilitation to Supervise Research document, Paris 6 University
Kenneth O. Stanley, Risto Miikkulainen (2004). Evolving a Roving Eye for Go. GECCO 2004

2005 ...

Tristan Cazenave, Bernard Helmstetter (2005). Combining tactical search and Monte-Carlo in the game of Go. IEEE CIG 2005, pdf, pdf
Tristan Cazenave (2005). The separation game. JCIS 2005, pdf
Shi-Jim Yen, Jr-Chang Chen (2005). Handtalk III wins 19x19 Go tournament. ICGA Journal, Vol. 28, No. 3 » 10th Computer Olympiad
Shi-Jim Yen, Jeng-Chi Yan (2005). Go Intellect wins 9x9 Go tournament. ICGA Journal, Vol. 28, No. 3 » 10th Computer Olympiad
Xiaozhen Niu, Akihiro Kishimoto, Martin Müller (2005). Recognizing Seki in Computer Go. Advances in Computer Games 11
Bruno Bouzy (2005). Move-Pruning Techniques for Monte-Carlo Go. Advances in Computer Games 11
Bruno Bouzy (2005). Associating domain-dependent knowledge and Monte Carlo approaches within a go program. Information Sciences, Heuristic Search and Computer Game Playing IV
Thomas Philip Runarsson, Simon Lucas (2005). Coevolution versus self-play temporal difference learning for acquiring position evaluation in small-board go. IEEE Transactions on Evolutionary Computation, Vol. 9, No. 6
Erik van der Werf, Mark Winands, Jaap van den Herik, Jos Uiterwijk (2005). Learning to predict life and death from Go game records. Information Sciences, Vol. 175, No. 4
Erik van der Werf, Jaap van den Herik, Jos Uiterwijk (2005). Learning to score final positions in the game of Go. Theoretical Computer Science, Vol. 349, No. 2, pdf preprint

2006

Ken Chen, Peigang Zhang (2006). A New Heuristic Search Algorithm for Capturing Problems in Go. CG 2006
Xiaozhen Niu, Martin Müller (2006). An Open Boundary Safety-of-Territory Solver for the Game of Go. CG 2006
Jahn-Takeshi Saito, Guillaume Chaslot, Jos Uiterwijk, Jaap van den Herik (2006). Monte-Carlo Proof-Number Search for Computer Go. CG 2006
Tristan Cazenave (2006). Virtual Global Search: Application to 9×9 Go. CG 2006
Rémi Coulom (2006). Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search. CG 2006, pdf
John Tromp, Gunnar Farnebäck (2006). Combinatorics of Go. CG 2006
Rémi Coulom, Ken Chen (2006). Crazy Stone wins 9x9 Go tournament. ICGA Journal, Vol. 29, No. 2 » 11th Computer Olympiad
Rémi Coulom, Ken Chen (2006). Gnu Go wins 19x19 Go tournament. ICGA Journal, Vol. 29, No. 2 » 11th Computer Olympiad
Bruno Bouzy (2006). History and Territory Heuristics for Monte-Carlo Go. New Mathematics and Natural Computation
Haruhiro Yoshimoto, Kazuki Yoshizoe, Tomoyuki Kaneko, Akihiro Kishimoto, Kenjiro Taura (2006). Monte Carlo Go Has a Way to Go. AAAI 2006, pdf
Julio César Hernández-Castro, Ignacio Blasco-López, Juan M. Estevez-Tapiador, Arturo Ribagorda-Garnacho (2006). Steganography in games: A general methodology and its application to the game of Go. Computers & Security, Vol. 25, pdf ⁴²

2007

Kazuki Yoshizoe, Akihiro Kishimoto, Martin Müller (2007). Lambda Depth-First Proof-Number Search and Its Application to Go. 20th IJCAI, pdf » Proof-Number Search
David Silver, Richard Sutton, Martin Müller (2007). Reinforcement learning of local shape in the game of Go. 20th IJCAI, pdf
Tristan Cazenave (2007). Playing the Right Atari. ICGA Journal, Vol. 30, No. 1, pdf
Erik van der Werf (2007). Steenvreter wins 9x9 Go tournament. ICGA Journal, Vol. 30, No. 2 » 12th Computer Olympiad#Go9x9
Sylvain Gelly, Yizao Wang (2007). MoGo wins 19x19 Go tournament. ICGA Journal, Vol. 30, No. 2 » 12th Computer Olympiad#Go
Ken Chen, Peigang Zhang (2007). Monte-Carlo Go with Knowledge-Guided Simulations. CGW 2007
Esa A. Seuranen (2007). Introducing Playing Style to Computer Go. CGW 2007, pdf
Thomas Wolf, Lei Shen (2007). Checking Life & Death Problems in Go. I: The Program SCANLD. CGW 2007, pdf
Rémi Coulom (2007). Computing Elo Ratings of Move Patterns in the Game of Go. CGW 2007
Rémi Coulom (2007). Computing Elo Ratings of Move Patterns in the Game of Go. ICGA Journal, Vol. 30, No. 4, pdf
Nobuo Araki, Kazuhiro Yoshida, Yoshimasa Tsuruoka, Jun'ichi Tsujii (2007). Move Prediction in Go with the Maximum Entropy Method. CIG 2007, pdf
Feng-hsiung Hsu (2007). Cracking GO. IEEE Spectrum, Vol. 44, No, 10 » Go

2008

Ken Chen, Peigang Zhang (2008). Monte-Carlo Go with Knowledge-Guided Simulations. ICGA Journal, Vol. 31, No. 2
Tristan Cazenave (2008). Multi-player Go. CG 2008
Ling Zhao, Martin Müller (2008). Using Artificial Boundaries in the Game of Go. CG 2008
Ken Chen, Dawei Du, Peigang Zhang (2008). A Fast Indexing Method for Monte-Carlo Go. CG 2008
Xiaozhen Niu, Martin Müller (2008). An Improved Safety Solver in Go Using Partial Regions. CG 2008
Guillaume Chaslot, Jean-Baptiste Hoock, Arpad Rimmel, Olivier Teytaud, Chang-Shing Lee, Mei-Hui Wang, Shang-Rong Tsai, Shun-Chin Hsu (2008). Human-Computer Go Revolution 2008. ICGA Journal, Vol. 31, No. 3
Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi (2008). Evaluation of Monte Carlo tree search and the application to Go. CIG 2008
Peigang Zhang, Ken Chen (2008). Monte-Carlo Go Capturing Tactic Search. New Mathematics and Natural Computation, Vol. 4, No. 3
Ilya Sutskever, Vinod Nair (2008). Mimicking Go Experts with Convolutional Neural Networks. ICANN 2008, pdf
Thomas Wolf (2008). Mastering Ladders. Slate & Shell

2009

Esa A. Seuranen (2009). Entropy in Go. ICGA Journal, Vol. 32, No. 1
Mark Winands (2009). Many Faces of Go wins 9x9 and 19x19 Go tournaments. ICGA Journal, Vol. 32, No. 1 » 13th Computer Olympiad
Markus Enzenberger, Martin Müller (2009). Fuego - An Open-source Framework for Board Games and Go Engine Based on Monte-Carlo Tree Search. Technical Report TR 09-08, University of Alberta
Martin Müller (2009). Fuego at the Computer Olympiad in Pamplona 2009: A Tournament Report. TR09-09
Rémi Coulom (2009). The Monte-Carlo Revolution in Go. JFFoS'2008: Japanese-French Frontiers of Science Symposium, slides as pdf
Chang-Shing Lee, Mei-Hui Wang, Guillaume Chaslot, Jean-Baptiste Hoock, Arpad Rimmel, Olivier Teytaud, Shang-Rong Tsai, Shun-Chin Hsu, Tzung-Pei Hong (2009). The Computational Intelligence of MoGo Revealed in Taiwan's Computer Go Tournaments. pdf
Chang-Shing Lee, Mei-Hui Wang, Tzung-Pei Hong, Guillaume Chaslot, Jean-Baptiste Hoock, Arpad Rimmel, Olivier Teytaud, Yau-Hwang Kuo (2009). A Novel Ontology for Computer Go Knowledge Management. IEEE FUZZ (2009), pdf
Vincent Berthier, Amine Bourki, Matthieu Coulm, Guillaume Chaslot, Christophe Fiter, Sylvain Gelly, Jean-Baptiste Hoock, Rémi Munos, Julien Pérez, Arpad Rimmel, Philippe Rolet, Olivier Teytaud, Paul Vayssière, Yizao Wang, Ziqin Yu (et al.) (2009). Computer-Go is not only for Go. Korea, August 2009 slides as pdf
Erik van der Werf, Mark Winands (2009). Solving Go for Rectangular Boards. ICGA Journal, Vol. 32, No. 2
Ken Chen (2009). Fuego wins 9x9 Go tournaments. ICGA Journal, Vol. 32, No. 2 » 14th Computer Olympiad
Ken Chen (2009). Zen wins 19x19 Go tournaments. ICGA Journal, Vol. 32, No. 2 » 14th Computer Olympiad
Ken Chen, Dawei Du, Peigang Zhang (2009). Monte-Carlo Tree Search and Computer Go. Advances in Information and Intelligent Systems 2009
Seth Pellegrino, Andrew Hubbard, Jason Galbraith, Peter D. Drake, Yung-Pin Chen (2009). Localizing Search in Monte-Carlo Go using Statistical Covariance. ICGA Journal, Vol. 32, No. 3
Thomas Wolf (2009). A library of eyes in Go, I: A life & death definition consistent with `bent-4. in Michael H. Albert, Richard J. Nowakowski (eds) (2009). Games of No Chance 3. Cambridge University Press, pdf
Thomas Wolf, Matthew Pratola (2009). A library of eyes in Go, II: Monolithic eyes. in Michael H. Albert, Richard J. Nowakowski (eds) (2009). Games of No Chance 3. Cambridge University Press, pdf

2010 ...

Frank Karger, Michael Babar (2010). MyGoFriend wins Go 9x9 Tournament. ICGA Journal, Vol. 33, No. 3 » 15th Computer Olympiad
Shih-Chieh Huang, Shi-Jim Yen (2010). Many Faces of Go wins Go 13x13 Tournament. ICGA Journal, Vol. 33, No. 3 » 15th Computer Olympiad
David Fotland (2010). Erica wins Go 19x19 Tournament. ICGA Journal, Vol. 33, No. 3 » 15th Computer Olympiad
Shih-Chieh Huang, Rémi Coulom, Shun-Shii Lin (2010). Monte-Carlo Simulation Balancing applied to 9x9 Go. ICGA Journal, Vol. 33, No. 4
Krzysztof Krawiec, Marcin Szubert (2010). Coevolutionary Temporal Difference Learning for small-board Go. IEEE Congress on Evolutionary Computation
Hendrik Baier (2010). Adaptive Playout Policies for Monte-Carlo Go. Master's thesis, University of Osnabrück, pdf
Hendrik Baier, Peter D. Drake (2010). The power of forgetting: Improving the last-good-reply policy in Monte Carlo Go. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 4
Chang-Shing Lee, Mei-Hui Wang, Shi-Jim Yen, Yu-Jen Chen, Cheng-Wei Chou, Guillaume Chaslot, Jean-Baptiste Hoock, Arpad Rimmel, Hassen Doghmen (2010). An ontology-based fuzzy inference system for computer Go applications. International Journal of Fuzzy Systems, Vol. 12, No. 2, pdf
Jean-Baptiste Hoock, Chang-Shing Lee, Arpad Rimmel, Fabien Teytaud, Mei-Hui Wang, Olivier Teytaud (2010). Intelligent Agents for the Game of Go. IEEE Computational Intelligence Magazine, Vol. 5, pdf

2011

Markus Enzenberger, Martin Müller, Broderick Arneson, Richard Segal (2011). Fuego - An Open-source Framework for Board Games and Go Engine Based on Monte-Carlo Tree Search. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 4, pdf
Abdallah Saffidine (2011). Moccos wins the Panthom-Go Tournament. ICGA Journal, Vol. 34, No. 1 » 15th Computer Olympiad
Ingo Althöfer (2011). John Tromp in the Style of David Levy: 4-0 win in the Go bet. ICGA Journal, Vol. 34, No. 2 » John Tromp ⁴³
Shih-Chieh Huang, Rémi Coulom, Shun-Shii Lin (2011). Time Management for Monte-Carlo Tree Search Applied to the Game of Go. TAAI 2010, pdf
Shih-Chieh Huang (2011). New Heuristics for Monte Carlo Tree Search Applied to the Game of Go. Ph.D. thesis, pdf
Hendrik Baier, Mark Winands (2011). Active Opening Book Application for Monte-Carlo Tree Search in 19x19 Go. BNAIC 2011, pdf
Petr Baudiš, Jean-Loup Gailly (2011). Pachi: State of the Art Open Source Go Program. Advances in Computer Games 13
Hendrik Baier, Mark Winands (2011). Time Management for Monte-Carlo Tree Search in Go. Advances in Computer Games 13
Cheng-Wei Chou, Ping-Chiang Chou, Hassen Doghmen, Chang-Shing Lee, Tsan-Cheng Su, Fabien Teytaud, Olivier Teytaud, Hui-Ming Wang, Mei-Hui Wang, Li-Wen Wu, Shi-Jim Yen (2011). Towards a Solution of 7x7 Go with Meta-MCTS. Advances in Computer Games 13
Henry Brausen, Ryan B. Hayward, Martin Müller, Abdul Qadir, David Spies (2011). Blunder Cost in Go and Hex. Advances in Computer Games 13
Jiao Wang, Shiyuan Li, Jitong Chen, Xin Wei, Huizhan Lv, Xinhe Xu (2011). 4*4-Pattern and Bayesian Learning in Monte-Carlo Go. Advances in Computer Games 13
Sylvain Gelly, David Silver (2011). Monte-Carlo tree search and rapid action value estimation in computer Go. Artificial Intelligence, Vol. 175, No. 11
Łukasz Lew (2011). Modeling Go Game as a Large Decomposable Decision Process. Ph.D. thesis, University of Warsaw
Krzysztof Krawiec, Wojciech Jaśkowski, Marcin Szubert (2011). Evolving small-board Go players using Coevolutionary Temporal Difference Learning with Archives. Applied Mathematics and Computer Science, Vol. 21, No. 4
Thomas Wolf (2011). A Dynamical Systems Approach for Static Evaluation in Go. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 3, No 2, also arXiv:1108.4220 ⁴⁴

2012

Sylvain Gelly, Marc Schoenauer, Michèle Sebag, Olivier Teytaud, Levente Kocsis, David Silver, Csaba Szepesvári (2012). The Grand Challenge of Computer Go: Monte Carlo Tree Search and Extensions. Communications of the ACM, Vol. 55, No. 3, pdf preprint
Chang-Shing Lee, Mei-Hui Wang, Olivier Teytaud, Shi-Jim Yen (2012). Human vs. Machine Go Competitions in IEEE WCCI 2012. ICGA Journal, Vol. 35, No. 4
Ching-Nung Lin, Shi-Jim Yen (2012). The Computer Go Tournaments in TCGA 2012. ICGA Journal, Vol. 35, No. 4
Ping-Chiang Chou, Shi-Jim Yen, Cheng-Wei Chou, Ching-Nung Lin, Chang-Shing Lee, Olivier Teytaud, Hassen Doghmen (2012). A simple Tsumego Generator. GPW 2012

2013

Cheng-Wei Chou, Ching-Nung Lin, Shi-Jim Yen, Hideki Kato, Jr-Chang Chen (2013). The 6th GPW Cup 9x9 and 13x13 Computer Go Tournaments. ICGA Journal, Vol. 36, No. 1
Ching-Nung Lin, Shi-Jim Yen (2013). The TAAI 2012 Computer Go Tournaments and Human vs. Computer Go Competition. ICGA Journal, Vol. 36, No. 1
Mark Boon (2013). The Beginning of Computer-Go Programs. ICGA Journal, Vol. 36, No. 2
Kokolo Ikeda, Simon Viennot (2013). Production of various strategies and position control for Monte-Carlo Go - Entertaining human players. CIG 2013
Shih-Chieh Huang, Martin Müller (2013). Investigating the Limits of Monte Carlo Tree Search Methods in Computer Go. CG 2013
Tobias Graf, Lars Schaefers, Marco Platzner (2013). On Semeai Detection in Monte-Carlo Go. CG 2013, pdf ⁴⁵
Sumudo Fernando, Martin Müller (2013). Analyzing Simulations in Monte-Carlo Tree Search for the Game of Go. CG 2013
David Silver, Richard Sutton, Martin Mueller (2013). Temporal-Difference Search in Computer Go. Proceedings of the ICAPS-13 Workshop on Planning and Learning, pdf
Katja Grace (2013). Algorithmic Progress in Six Domains. Technical report 2013-3, Machine Intelligence Research Institute, Berkeley, CA, pdf, 5 Game Playing, 5.1 Chess, 5.2 Go, 9 Machine Learning
Chun-Hsiang Hsieh, Jeng-Chi Yan (2013). The Design and Development of a 9 by 9 GO Opening Game Knowledge Base System. International Journal of Information and Education Technology, Vol. 3, No. 4
Chang-Shing Lee, Mei-Hui Wang, Yu-Jen Chen, Shi-Jim Yen (2013). Apply Fuzzy Markup Language to Knowledge Representation for Game of Computer Go. in Giovanni Acampora, Vincenzo Loia, Chang-Shing Lee, Mei-Hui Wang (eds.) (2013). On the Power of Fuzzy Markup Language. Studies in Fuzziness and Soft Computing, Vol. 296, Springer ⁴⁶

2014

Lars Schaefers (2014). Parallel Monte-Carlo Tree Search for HPC Systems and its Application to Computer Go. Ph.D. thesis, Paderborn University, advisors Marco Platzner, Ulf Lorenz, pdf, pdf
S. Ali Mirsoleimani, Aske Plaat, Jaap van den Herik, Jos Vermaseren (2014). Performance analysis of a 240 thread tournament level MCTS Go program on the Intel Xeon Phi. CoRR abs/1409.4297 » MCTS, Parallel Search, x86-64
Christopher Clark, Amos Storkey (2014). Teaching Deep Convolutional Neural Networks to Play Go. arXiv:1412.3409 » DCNN in Go
Chris J. Maddison, Aja Huang, Ilya Sutskever, David Silver (2014). Move Evaluation in Go Using Deep Convolutional Neural Networks. arXiv:1412.6564v1 » DCNN in Go
Ingo Althöfer, Raymond Georg Snatzke (2014). The codecentric Go Challenge 2014: Franz-Josef Dickhut vs. CRAZY STONE. ICGA Journal, Vol. 37, No. 4 ⁴⁷ ⁴⁸ ⁴⁹

2015 ...

Olivier Teytaud, Abdallah Saffidine, Shi-Jim Yen (2015). The complexities of Go. Advances in Computer Games 14
Kokolo Ikeda, Takanari Shishido, Simon Viennot (2015). Machine-Learning of Shape Names for the Game of Go. Advances in Computer Games 14
Yuandong Tian, Yan Zhu (2015). Better Computer Go Player with Neural Network and Long-term Prediction. arXiv:1511.06410 ⁵⁰ ⁵¹ » Neural Networks
Thomas Wolf (2015). A Classification of Semeai with Approach Moves. ICGA Journal, Vol. 38, No. 4, arXiv:1608.02890
Peter H. Jin, Kurt Keutzer (2015). Convolutional Monte Carlo Rollouts in Go. arXiv:1512.03375
Lars Schaefers, Marco Platzner (2015). Distributed Monte Carlo Tree Search: A Novel Technique and its Application to Computer Go. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 7, No. 4 ⁵²
Martin Müller (2015). Keynote speech III Computer go research - The challenges ahead. CIG 2015

2016

John Tromp, Gunnar Farnebäck (2016). Combinatorics of Go. Revised Version of the CG 2006 Paper
David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis (2016). Mastering the game of Go with deep neural networks and tree search. Nature, Vol. 529 » AlphaGo
Tobias Graf, Marco Platzner (2016). Using Deep Convolutional Neural Networks in Monte Carlo Tree Search. CG 2016
John Tromp (2016). The number of legal Go positions. CG 2016
John Tromp, Matthieu Walraet (2016). A googolplex of Go games. CG 2016
Aja Huang (2016). AlphaGo: Combining Deep Neural Networks with Tree Search. CG 2016, Keynote Lecture
Ingo Althöfer (2016). Computer-Aided Go: Chess as a Role Model. CG 2016
Peter H. Jin , Kurt Keutzer (2016). Convolutional Monte Carlo Rollouts for Computer Go. CG 2016
Chang-Shing Lee, Mei-Hui Wang, Shi-Jim Yen, Ting-Han Wei, I-Chen Wu, Ping-Chiang Chou, Chun-Hsun Chou, Ming-Wan Wang, Tai-Hsiung Yang (2016). Human vs. Computer Go: Review and Prospect. arXiv:1606.02032
Jonathan Rosenthal (2016). Deep Learning for Go. B.Sc. thesis, ETH Zurich
Kokolo Ikeda, Simon Viennot, Naoyuki Sato (2016). Detection and labeling of bad moves for coaching go. CIG 2016
Chenjun Xiao, Martin Müller (2016). Factorization Ranking Model for Move Prediction in the Game of Go. AAAI 2016

2017

Tristan Cazenave (2017). Residual Networks for Computer Go. IEEE Transactions on Computational Intelligence and AI in Games, Vol. PP, No. 99, pdf
Ti-Rong Wu, I-Chen Wu, Guan-Wun Chen, Ting-Han Wei, Tung-Yi Lai, Hung-Chun Wu, Li-Cheng Lan (2017). Multi-Labelled Value Networks for Computer Go. arXiv:1705.10701
Tristan Cazenave (2017). Improved Policy Networks for Computer Go. Advances in Computer Games 15, pdf
Thomas Wolf (2017). Seki with 2 Liberties per Chain in the Game of Go. ICGA Journal, Vol. 39, No. 2
Jon Diamond (2017). A History of Go-playing Programs. ICGA Journal, Vol. 39, No. 2
Chang-Shing Lee, Mei-Hui Wang, Chia-Hsiu Kao, Sheng-Chi Yang, Yusuke Nojima, Ryosuke Saga, Nan Shuo, Naoyuki Kubota (2017). FML-based Prediction Agent and Its Application to Game of Go. arXiv:1704.04719
Chang-Shing Lee, Mei-Hui Wang, Sheng-Chi Yang, Pi-Hsia Hung, Su-Wei Lin, Nan Shuo, Naoyuki Kubota, Chun-Hsun Chou, Ping-Chiang Chou, Chia-Hsiu Kao (2017). FML-based Dynamic Assessment Agent for Human-Machine Cooperative System on Game of Go. arXiv:1707.04828
David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel, Demis Hassabis (2017). Mastering the game of Go without human knowledge. Nature, Vol. 550, pdf
David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis (2017). Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. arXiv:1712.01815 » AlphaZero

2018

Chang-Shing Lee, Mei-Hui Wang, Li-Wei Ko, Naoyuki Kubota, Lu-An Lin, Shinya Kitaoka, Yu-Te Wang, Shun-Feng Su (2018). Human and Smart Machine Co-Learning with Brain Computer Interface. arXiv:1802.06521
David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis (2018). A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, Vol. 362, No. 6419 ⁵³
Yuuto Kosaka, Takeshi Ito (2018). Examination of Indicators for Estimating Players’ Strength by using Computer Go. TAAI 2018
Chung-Chin Shih, An-Jen Liu, I-Chen Wu (2018). 2017 “CITIC Securities Cup” – The 1st World AI Go Open. ICGA Journal, Vol. 40, No. 4

2019

Chang-Shing Lee, Mei-Hui Wang, Li-Wei Ko, Bo-Yu Tsai, Yi-Lin Tsai, Sheng-Chi Yang, Lu-An Lin, Yi-Hsiu Lee, Hirofumi Ohashi, Naoyuki Kubota, Nan Shuo (2019). PFML-based Semantic BCI Agent for Game of Go Learning and Prediction. arXiv:1901.02999
Chang-Shing Lee, Mei-Hui Wang, Li-Chuang Chen, Yusuke Nojima, Tzong-Xiang Huang, Jinseok Woo, Naoyuki Kubota, Eri Sato-Shimokawara, Toru Yamaguchi (2019). A GFML-based Robot Agent for Human and Machine Cooperative Learning on Game of Go. arXiv:1901.07191
Yuandong Tian, Jerry Ma, Qucheng Gong, Shubho Sengupta, Zhuoyuan Chen, James Pinkerton, C. Lawrence Zitnick (2019). ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero. arXiv:1902.04522 ⁵⁴ ⁵⁵
David J. Wu (2019). Accelerating Self-Play Learning in Go. arXiv:1902.10565 ⁵⁶
Yusaku Mandai, Tomoyuki Kaneko (2019). RankNet for evaluation functions of the game of Go. ICGA Journal, Vol. 41, No. 2
Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, Karen Simonyan, Laurent Sifre, Simon Schmitt, Arthur Guez, Edward Lockhart, Demis Hassabis, Thore Graepel, Timothy Lillicrap, David Silver (2019). Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. arXiv:1911.08265 ⁵⁷
Hsiao-Chung Hsieh, Ti-Rong Wu, Ting-Han Wei, I-Chen Wu (2019). Net2Net Extension for the AlphaGo Zero Algorithm. Advances in Computer Games 16