Updated Nov 7, 2024.
This page lists publications which include at least one member of my research group. Contents are sorted by date, most recent first. Students or employees (co-)supervised by me in bold, supervised by others at University of Alberta in italic.
H. Du and M. Müller. Solving Linear NoGo with Combinatorial Game Theory. Accepted, Computers and Games 2024.
A. Husna and M. Müller. Analysing KataGo: A Comparative Evaluation Against Perfect Play in the Game of Go. Accepted, Computers and Games 2024.
H. Zhang and C. Xiao and C. Gao and H. Wang and B. Xu and M. Müller. Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration. Accepted, NeurIPS 2024.
H. Zhang and K. Sun and B. Xu and L. Kong and M. Müller. A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning. TMLR 2024.
S. Chowdhury, M. Müller and J.-H. You. Exploring Conflict Generating Decisions: Initial Results (Extended Abstract). SOCS 2024, 267-268.
T. Bertram, J. Fürnkranz and M. Müller. Neural Network-based Information Set Weighting for Playing Reconnaissance Blind Chess. Accepted for IEEE Transactions on Games (early access). This is an extended version of our paper in IEEE Conference on Games 2023.
T. Bertram, J. Fürnkranz and M. Müller. Efficiently Training Neural Networks for Imperfect-Information Games by Sampling Information Sets. KI 24, p. 17--29, Springer LNCS 14992. https://doi.org/10.1007/978-3-031-70893-0_2
A. Husna. Analyzing KataGo: A comparative evaluation against perfect play in the game of Go. MSc thesis, University of Alberta, 2024.
O. Randall, T.-h. Wei, R. Hayward and M. Müller. Expected Work Search: Combining Win Rate and Proof Size Estimation. IJCAI, p. 7003-7011, 2024, DOI 10.24963/ijcai.2024/774
Best student paper award
T. Bertram, J. Fürnkranz and M. Müller.
Learning With Generalised Card Representations for
"Magic: The Gathering".
IEEE Conference on Games, p. 1-8, 2024, DOI 10.1109/CoG60054.2024.10645602.
H. Zhang, T. Ren, C. Xiao, D. Schuurmans and B. Dai. Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning. ICML 2024, Proceedings of Machine Learning Research PMLR 235, p. 59759-59782.
E. Futuhi. Improving Deep Deterministic Policy Gradient for sparse reward and goal-conditioned continuous control. MSc thesis, University of Alberta, 2024.
F. Kohankhaki, K. Aghakasiri, H. Zhang, T.-h. Wei, C. Gao and M. Müller. Monte Carlo Tree Search in the Presence of Transition Uncertainty. AAAI-24, 20151-20158, 2024.
F. Bai, H. Zhang, T. Tao, Z. Wu, Y. Wang and B. Xu. Picor: Multi-task deep reinforcement learning with policy correction. AAAI, p. 6728-6736, 2023.
Q. A. Sadmine, A. Husna, and M. Müller. Stockfish or Leela Chess Zero? A Comparison Against Endgame Tablebases. Advances in Computer Games (ACG) 2023, LNCS 14528, p. 26-35.
H. Du, T.-h. Wei, and M. Müller. Solving NoGo on Small Rectangular Boards. Advances in Computer Games (ACG) 2023, LNCS 14528, p. 39-49.
J. Wang, M. Müller and J. Schaeffer. Deep Dive on Checkers Endgame Data. IEEE Conference on Games, 8pp, 2023. DOI 10.1109/COG57401.2023.10333165 .
J. Wang. Deep Dive on Checkers Endgame Data. MSc thesis, University of Alberta, 2023.
T. Bertram, J. Fürnkranz and M. Müller. Weighting Information Sets with Siamese Neural Networks in Reconnaissance Blind Chess. IEEE Conference on Games, 8pp, 2023. DOI 10.1109/COG57401.2023.10333170 .
H. Zhang, C. Xiao, H. Wang, J. Jin, B. Xu and M. Müller. Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay. ICLR 2023.
C. Xiao. Advances in Simulation-Based Search and Batch Reinforcement Learning. PhD thesis, University of Alberta, 2023.
R. W. Gardner, G. Perrotta, A. Shah, S. Kalyanakrishnan, K. A. Wang, G. Clark, T. Bertram, J. Fürnkranz, M. Müller, B. P. Garrison, P. Dasgupta, S. Rezaei. The Machine Reconnaissance Blind Chess Tournament of NeurIPS 2022. Proceedings of the NeurIPS 2022 Competitions Track, PMLR 220:119-132, 2023.
O. Randall, T.-h. Wei, R. Hayward and M. Müller. Improving Search in Go Using Bounded Static Safety. Computers and Games (CG2022).
C.-C. Shih, T.-R. Wu, T.-h. Wei, I-C. Wu. A Novel Approach to Solving Goal-Achieving Problems for Board Games. AAAI 2022: 10362-10369
T.-R. Wu, C.-C. Shih, T.-h. Wei, M.-Y. Tsai, W.-Y. Hsu, I-C. Wu: AlphaZero-based Proof Cost Network to Aid Game Solving. ICLR 2022.
Z. Wang. MooZi: A High-Performance Game-playing System that Plans with a Learned Model. MSc thesis, University of Alberta, 2022. Also see the Github MooZi repository.
B. Tapkan. Dark Hex: A Large Scale Imperfect Information Game. MSc thesis, University of Alberta, 2022.
T. Bertram, J. Fürnkranz and M. Müller. Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess. IEEE Conference on Games (CoG) 2022.
A. Biere, S. Chowdhury, M. Heule, B. Kiesl, M. Whalen. Migrating solver state. SAT 22. Work done during Solimul's internship at Amazon.
K. Aghakasiri. Monte Carlo Tree Search in the Presence of Model Uncertainty. MSc thesis, University of Alberta, 2022.
F. Kohankhaki. Monte Carlo Tree Search and Model Uncertainty. MSc thesis, University of Alberta, 2022.
C. Xiao, B. Dai, J. Mei, O. Ramirez, R. Gummadi, C. Harris, and D. Schuurmans. Understanding and Leveraging Overparameterization in Recursive Value Estimation. International Conference on Learning Representations (ICLR), 2022.
C. Xiao, I. Lee, B. Dai, D. Schuurmans and C. Szepesvári. The Curse of Passive Data Collection in Batch Reinforcement Learning. International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
R. Haque. On the Road to Perfection? Evaluating LeelaChess Zero Against Endgame Tablebases. MSc thesis, University of Alberta, 2021.
S. Chowdhury. Empirical Insights Driven CDCL SAT Algorithms. PhD thesis, University of Alberta, 2021.
R. Haque, T.-h. Wei and M. Müller. On the Road to Perfection? Evaluating LeelaChess Zero Against Endgame Tablebases. Advances in Computer Games (ACG 2021).
T. Bertram, J. Fürnkranz and M. Müller. A Comparison of Contextual and Non-Contextual Preference Ranking for Set Addition Problems. In ICML 2021 workshop on Subset Selection in Machine Learning: From Theory to Applications, 2021.
Best paper award
T. Bertram, J. Fürnkranz and M. Müller.
Predicting Human Card Selection in Magic: The Gathering with Contextual Preference Ranking.
In IEEE COG 2021.
J. Mei, C. Xiao, C.Szepesvári, D. Schuurmans. On the Global Convergence Rates of Softmax Policy Gradient Methods. ICML 2020. PMLR 119:6820-6829, 2020.
C. Gao. Search and Learning Algorithms for Two-Player Games with Application to the Game of Hex. PhD thesis, University of Alberta, 2020.
S. Chowdhury, J. You and M. Müller. Guiding CDCL SAT search via random exploration amid conflict depression. AAAI-20, 1428--1435, 2020. Selected for Oral Presentation (5.8% of papers).
Y. Tang. An Empirical Study of Random Sampling Methods for Changing Discrete Distributions. MSc thesis, University of Alberta, 2019.
C. Xiao, R. Huang, J. Mei, D. Schuurmans and M. Müller. Maximum entropy Monte Carlo planning. NeurIPS 2019, 9516--9524, 2019.
C. Xiao, Y. Wu, C. Ma, D. Schuurmans, and M. Müller. Learning to combat compounding-error in model-based reinforcement learning. NeurIPS 2019 Deep RL Workshop.
S. Chowdhury, J. You and M. Müller.
Exploiting glue clauses to design effective CDCL
branching heuristics.
CP'2019, pages 126-143.
J. Mei, C. Xiao, R. Huang, D. Schuurmans and M. Müller. On principled entropy exploration in policy optimization. IJCAI 2019, pages 3130-3136.
X. Qin, V. Zhang, C. Huang, M. Dehghan, C. Gao and M. Jagersand. BASNet: Boundary aware salient object detection. CVPR 2019, pages 7479-7489.
C. Gao, K. Takada and R. Hayward. Hex 2018: MoHex3HNN over DeepEzo, ICGA Journal 41(1), 39-42, 2019.
G. Fan. Understanding and Improving Merge-and-Shrink Abstraction for Cost Optimal Planning. PhD thesis, University of Alberta, 2019.
C. Gao,
P. Hernandez-Leal, B. Kartal and M. Taylor.
Skynet: A top deep RL agent in the inaugural
Pommerman team competition.
In 4th Multidisciplinary
Conference on Reinforcement Learning
and Decision Making, 2019.
Chao's internship at
Borealis AI
led to this paper.
B. Kartal, P. Hernandez-Leal,
C. Gao
and M. Taylor.
Safer deep RL with shallow MCTS: A case study in Pommerman.
AAMAS Workshop on Adaptive Learning Agents, 2019.
Chao's internship at
Borealis AI
led to this paper.
S. Chowdhury, M. Müller and J.-H. You. Characterization of Glue Variables in CDCL SAT Solving. arxiv.org/abs/1904.11106, 2019.
F. Haqiqat and M. Müller.
Analyzing the impact of knowledge and search
in Monte Carlo Tree Search in Go.
In
CGW, the Computer Games Workshop
at IJCAI 2018.
S. Chowdhury, M. Müller and J. You.
Description of expSAT Solvers. Abstract.
Pages 22-23 in M. Heule and M. Järvisalo and M. Suda (editors)
Proceedings of SAT Competition 2018,
Department of Computer Science, University of Helsinki.
S. Chowdhury, M. Müller and J. You.
GrandTour-obs Puzzle as a SAT Benchmark. Abstract.
Pages 59-60 in M. Heule and M. Järvisalo and M. Suda (editors)
Proceedings of SAT Competition 2018,
Department of Computer Science, University of Helsinki.
C. Gao, S. Yan,
R. Hayward and M. Müller.
A Transferable Neural Network for Hex.
ICGA Journal 40(3), 224-233, 2018.
Conference version from
CG 2018,
the 10th International Conference on Computers and Games,
New Taipeh City, Taiwan.
F. Haqiqat. Analyzing the impact of knowledge and search in Monte Carlo Tree Search in Go. MSc thesis, University of Alberta, 2018.
C. Gao,
R. Hayward and M. Müller.
Three-Head Neural Network Architecture for Monte Carlo Tree Search.
IJCAI-ECAI , pages 3762-3768, Stockholm 2018.
C. Gao
, M. Müller and R. Hayward.
Adversarial
Policy Gradient for Alternating Markov Games.
In
ICLR 2018 Workshop Track. 16 pages, 2018.
G. Fan, R. Holte and M. Müller.
MS-lite: A Lightweight, Complementary Merge-and-Shrink Method.
In
ICAPS 2018, pages 74-82. Delft, The Netherlands, 2018.
C. Xiao,
J. Mei
and M. Müller.
Memory-Augmented Monte Carlo Tree Search.
AAAI-18, pages 1455-1461.
Outstanding paper award.
Also see the slides for Chenjun's talk at AAAI.
S. Chowdhury, M. Müller and J. You. Exploration-Driven Satisfiability Solving: First Results. AAAI-18, pages 8069-8070, student abstract.
C. Gao, R. Hayward and M. Müller. Move Prediction using Deep Convolutional Neural Networks in Hex. IEEE Transactions on Games 10(4), 336-343, 2018.
I.-C. Wu, C.-S. Lee, Y. Tian and M. Müller. Guest editors, IEEE Transactions on Games, Special Issue on Deep/Reinforcement Learning and Games. Issue 10(4), 2018. Guest editorial on pages 333 - 335.
R. Huang, M. Ajallooeian, C. Szepesvári and M. Müller. Structured Best Arm Identification with Fixed Confidence. ALT 2017, Proceedings of the 28th International Conference on Algorithmic Learning Theory. Published in PMLR 76, 593-616, 2017.
G. Fan, R. Holte and M. Müller. Additive merge-and-shrink heuristics for diverse action costs. IJCAI 2017, 4287-4293.
C. Gao, R. Hayward and M. Müller. Focused Depth-first Proof Number Search using Convolutional Neural Networks for the Game of Hex. IJCAI 2017, 3668-3674.
F. Xie, A. Botea and A. Kishimoto.
A Scalable Approach to Chasing Multiple Moving Targets with
Multiple Agents.
IJCAI 2017.
Fan's internship at IBM Research in Dublin, which led to this paper,
also led to a
US Patent Application (!)
for
"Pro-active fuel and battery refilling for vehicles".
G. Fan, M. Müller and R. Holte. The two-edged nature of diverse action costs. ICAPS 2017, 98-106.
G. Fan. Diverse Action Costs in Heuristic Search and Planning. In AI 2017: Advances in Artificial Intelligence, Springer LNCS 10233, 399-402, 2017.
C. Xiao and M. Müller. Integrating factorization ranked features into MCTS: an experimental study. Computer Games Workshop at IJCAI, 34-43, 2016.
C. Xiao. Factorization Ranking Model for Move Prediction in the Game of Go. MSc thesis, University of Alberta, 2016.
K. Yoshizoe and M. Müller. Computer Go. Encyclopedia of Computer Graphics and Games, editor N. Lee, Springer International, ISBN 978-3-319-08234-9, pages 1-13, 2016.
A. Kishimoto and M. Müller. Game Solvers. Handbook of Digital Games and Entertainment Technologies, editors R. Nakatsu, M. Rauterberg, and P.Ciancarini, ISBN 978-981-4560-52-8, pages 1-20, Springer Singapore, 2016.
F. Xie. Exploration in Greedy Best-First Search for Satisficing Planning. PhD thesis, University of Alberta, 2016. Faculty of Science Dissertation Award
C. Xiao and M. Müller. Factorization Ranking Model for Move Prediction in the Game of Go. AAAI-16, pages 1359-1365. Also see the poster.
R. Valenzano and F. Xie. On the Completeness of Best-First Search Variants that Use Random Exploration. AAAI-16, pages 784-790, 2016.
W. Chen. Motion Planning with Monte Carlo Random Walks. MSc thesis, University of Alberta, 2015.
W. Chen and M. Müller. Continuous Arvand: Motion Planning with Monte Carlo Random Walks. 3rd ICAPS Workshop on Planning and Robotics (PlanRob 2015), pages 23-34. (pre-print)
F. Xie, M. Müller and R. Holte. Understanding and Improving Local Exploration for GBFS. ICAPS 2015, pages 244-248.
F. Xie, A. Botea and A. Kishimoto. Heuristic-Aided Compressed Distance Databases. AAAI-2015 Workshop on Planning, Search and Optimization, pages 85-91, 2015.
Y. Zhang and M. Müller. TDS+: Improving Temperature Discovery Search. AAAI 2015, pages 1241-1247.
J. Song and M. Müller. An Enhanced Solver for The Game of Amazons. IEEE Transactions on Computational Intelligence and AI in Games (TCIAIG) 7(1), 16-27, 2015.
Y. Zhang. TDS+: Improving Temperature Discovery Search. MSc thesis, University of Alberta, 2015.
J. Schaeffer, M. Müller and A. Kishimoto, Go-bot, Go. IEEE Spectrum 51(7), 48-53, 2014. Published online under the title: AIs Have Mastered Chess. Will Go Be Next?.
G. Fan, M. Müller and R. Holte. Non-Linear Merging Strategies for Merge-and-Shrink Based on Variable Interactions. SOCS, p. 53-61, 2014.
M. Müller and K. Yoshizoe. Fuego - an Open Source Software for Playing the Game of Go. Abstract, Replaying Japan 2014, p. 20-21.
R. Valenzano, H. Nakhost, M. Müller, J. Schaeffer and N. Sturtevant. ArvandHerd 2014. In M. Vallati, L. Chrpa, L. and T. McCluskey, The Eighth International Planning Competition, University of Huddersfield, p. 1-5, 2014.
F. Xie, M. Müller and R. Holte.
Jasper: the Art of Exploration in Greedy Best First Search.
In M. Vallati, L. Chrpa, L. and T. McCluskey,
The Eighth International Planning Competition, University of Huddersfield,
p. 39-42,
2014.
Update Nov 28, 2014: the version linked above replaces the IPC
booklet version. It fixes a typo in Table 1: the coverage of LAMA-2011
was 1913 out of a total of 2112, not 2113.
F. Xie, M. Müller and R. Holte. Adding Local Exploration to Greedy Best-First Search for Satisficing Planning . AAAI 2014, p. 2388-2394, 2014.
F. Xie, M. Müller, R. Holte and T. Imai. Type-based Exploration for Satisficing Planning with Multiple Search Queues . AAAI 2014, p. 2395-2401, 2014.
R. Valenzano, N. Sturtevant, J. Schaeffer and F. Xie. A Comparison of Knowledge-Based GBFS Enhancements and Knowledge-Free Exploration. ICAPS 2014, p. 375-379, 2014.
F. Xie, M. Müller and R. Holte. Adding Local Exploration to Greedy Best-First Search in Satisficing Planning. ICAPS-2014 Workshop on Heuristics and Search for Domain-independent Planning, 53-61. A slightly extended version of the AAAI paper above. 2014.
F. Xie, M. Müller, R. Holte and T. Imai. Type-based Exploration with Multiple Search Queues for Satisficing Planning. ICAPS-2014 Workshop on Heuristics and Search for Domain-independent Planning, 62-70. A slightly extended version of the AAAI paper above. 2014.
A. Couëtoux, M. Müller and O. Teytaud. Monte Carlo Tree Search in Go. 32 pp. Book chapter draft, 2013. (pre-print)
H. Nakhost and M. Müller. Towards a Theory of Random Walk Planning: Regress Factors, Fair Homogeneous Graphs, and Extensions. AI Communications 27, 329-344. 2014. (pre-print)
H. Nakhost. Random Walk Planning: Theory, Practice, and Application. PhD thesis, University of Alberta, 2013. Dissertation Award for best PhD thesis from the Canadian Artificial Intelligence Association.
S.-C. Huang, B. Arneson, R. Hayward, M. Müller and J. Pawlewicz. MoHex 2.0: a pattern-based MCTS Hex player. Computers and Games 2013, p. 60-71.
S.-C. Huang and M. Müller.
Investigating the Limits of Monte Carlo Tree Search Methods in Computer Go.
Computers and Games 2013, p. 39-48.
Erratum for this paper - in test case 2 Black wins.
S. Fernando and M. Müller. Analyzing Simulations in Monte Carlo Tree Search for the Game of Go. Computers and Games 2013, p. 72-83.
C. Hunt and M. Müller. Fuegito: an Educational Software Package for Game Tree Search. Technical report TR 13-03, Dept. of Computing Science, University of Alberta, 2013.
H. Nakhost and M. Müller. Towards a second generation random walk planner: an experimental exploration. IJCAI 2013, pages 2336-2342. Errata for this paper.
D. Silver, R. Sutton and M. Müller. Temporal-difference search in computer Go. Refereed abstract. ICAPS 2013 Journal Presentation Track, pages 486-487, AAAI Press, 2013.
F. Xie, R. Valenzano and M. Müller. Better time constrained search via randomization and postprocessing. ICAPS 2013, pages 269-277, 2013.
F. Xie, R. Valenzano and M. Müller. Better time constrained search via randomization and postprocessing. Technical Report TR 13-02, Dept. of Computing Science. University of Alberta, Edmonton, Alberta, Canada, 2013.
A. Kishimoto, M. Winands, M. Müller and J. Saito.
Game-Tree Search Using Proof Numbers: The First Twenty Years.
ICGA Journal 35(3), 131-156, 2012.
Erratum for this article - see here.
J. Song. An enhanced solver for the game of Amazons. MSc thesis, University of Alberta, 2012.
C. Hunt. Fuegito User Manual. Technical Report TR12-05, University of Alberta, 2012.
G. Van Eyck. Move Groups as a General Enhancement for Monte Carlo Tree Search. MSc thesis, University of Alberta, 2014.
H. Nakhost and M. Müller. A Theoretical Framework for Studying Random Walk Planning. In SOCS, 2012.
R. Valenzano, H. Nakhost, M. Müller, J. Schaeffer, and N. Sturtevant. ArvandHerd: Parallel Planning with a Portfolio. In ECAI, 2012.
D. Silver, R. Sutton and M. Müller. Temporal-Difference Search in Computer Go. Machine Learning 87(2), 183-219, 2012.
H. Nakhost, J. Hoffmann and M. Müller. Resource-Constrained Planning: A Monte Carlo Random Walk Approach. In ICAPS, 2012.
F. Xie, H. Nakhost and M. Müller. Planning via Random Walk-Driven Local Search. In ICAPS, 2012.
J. Styles, H. Hoos and M. Müller. Automatically Configuring Algorithms for Scaling Performance. In Learning and Intelligent OptimizatioN Conference, LION 6, 2012.
H. Brausen, R. Hayward, M. Müller, A. Qadir and D. Spies. Blunder cost in Go and Hex. In Advances in Computer Games 13, 2011.
G. Van Eyck and M. Müller. Revisiting Move Groups in Monte Carlo Tree Search. In Advances in Computer Games 13, 2011.
R. Valenzano, H. Nakhost, M. Müller, J. Schaeffer, and N. Sturtevant. ArvandHerd: Parallel Planning with a Portfolio. 2011 International Planning Competition (IPC 2011) Planner Description Booklet.
H. Nakhost, M. Müller, R. Valenzano, and F. Xie. Arvand: the Art of Random Walks. 2011 International Planning Competition (IPC 2011) Planner Description Booklet.
F. Xie, H. Nakhost and M. Müller. A Local Monte Carlo Tree Search Approach in Deterministic Planning. AAAI Conference on Artificial Intelligence Student Abstract and Poster Program (SA-11), pages 1832-1833, 2011.
D. Tom and M. Müller. Computational Experiments with the RAVE Heuristic. Lecture Notes in Computer Science 6515, pages 69-80, editors J. van den Herik, H. Iida and A. Plaat, Springer 2011.
M. Enzenberger, M. Müller, B. Arneson and R. Segal. 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, 2(4), 259-270. Special issue on Monte Carlo Techniques and Computer Go, 2010. (IEEE Explore or final author version)
M. Müller. Fuego-GB Prototype at the Human machine competition in Barcelona 2010: a Tournament Report and Analysis. Technical Report TR 10-08, Dept. of Computing Science, University of Alberta, Edmonton, Alberta, Canada, 2010.
D. Tom. Investigating UCT and RAVE: steps towards a more robust method. MSc thesis, University of Alberta, 2010.
H. Nakhost, J. Hoffmann and M. Müller. Improving Local Search for Resource-Constrained Planning. Extended abstract. Proceedings of the Third Annual Symposium on Combinatorial Search (SOCS-10), pages 81-82, Stone Mountain, Atlanta, GA, USA, 2010.
N. Burch, R. Holte, M. Müller, D. O'Connell and J. Schaeffer. Automating Layouts of Sewers in Subdivisions. ECAI 2010, pages 655-660, 2010.
H. Nakhost and M. Müller. Action Elimination and Plan Neighborhood Graph Search: Two Algorithms for Plan Improvement. International Conference on Automated Planning and Scheduling (ICAPS-2010), pages 121-128, 2010. Editors R. Brafman, H. Geffner, J. Hoffmann and H. Kautz. AAAI Press, Toronto, Canada.
H. Nakhost and M. Müller. Action Elimination and Plan Neighborhood Graph Search: Two Algorithms for Plan Improvement - Extended Version, 2010. Technical report TR 10-01, Dept. of Computing Science. University of Alberta.
H. Nakhost and M. Müller. Monte-Carlo exploration for deterministic planning. In Twenty-first International Joint Conference on Artificial Intelligence (IJCAI), pages 1766-1771, Pasadena, California, USA, 2009.
D. Silver. Reinforcement Learning and Simulation-Based Search in Computer Go. PhD thesis, University of Alberta, 2009.
D. Silver and G. Tesauro. Monte-Carlo simulation balancing. In Danyluk et al., ICML 2009.
R. Sutton, Hamid R. Maei, D. Precup, S. Bhatnagar, D. Silver, C. Szepesvári, and E. Wiewiora. Fast gradient-descent methods for temporal-difference learning with linear function approximation. In Danyluk et al., ICML 2009.
M. Enzenberger and M. Müller.
A lock-free multithreaded Monte-Carlo tree search algorithm.
Advances in Computer Games 12, LNCS 6048, pages 14-20, Springer, 2009.
Note: the reference [8] in the paper to Remi Coulom's messages is no longer
valid. Currently the first message as well as links to the whole thread
can be found
on this archive page.
D. Tom and M. Müller. A study of UCT and its enhancements, 2009. Advances in Computer Games 12, LNCS 6048, pages 55-64, Springer.
M. Enzenberger and M. Müller.
Fuego - an open-source framework for board games and Go engine
based on Monte-Carlo tree search.
Technical Report TR 09-08,
Dept. of Computing Science. University of
Alberta, Edmonton, Alberta, Canada, 2009.
Note: this report is superseded by the 2010 TCIAIG Journal paper
M. Müller. Fuego at the Computer Olympiad in Pamplona 2009: a tournament report. Technical Report TR 09-09, Dept. of Computing Science. University of Alberta, Edmonton, Alberta, Canada, 2009.
S. Gelly and D. Silver. Achieving master level play in 9 x 9 computer Go. In D. Fox and C. Gomes, editors, AAAI, pages 1537-1540. AAAI Press, 2008.
D. Silver, R. Sutton, and M. Müller. Sample-based learning and search with permanent and transient memories. In W. Cohen, A. McCallum, and S. Roweis, editors, Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), volume 307 of ACM International Conference Proceeding Series, pages 968-975, Helsinki, Finland, 2008. ACM.
X. Niu and M. Müller.
An improved safety solver in Go using partial regions.
In J. van den Herik, X. Xu, Z. Ma, and M. Winands, editors,
Computer and Games. 6th International Conference, volume 5131 of
Lecture Notes in Computer Science, pages 102-112, Beijing, China, 2008.
Springer.
DOI: http://dx.doi.org/10.1007/978-3-540-87608-3_10.
A. Kishimoto and M. Müller. About the completeness of depth-first proof-number search. In J. van den Herik, X. Xu, Z. Ma, and M. Winands, editors, Computer and Games. 6th International Conference, volume 5131 of Lecture Notes in Computer Science, pages 146-156, Beijing, China, 2008. Springer. http://dx.doi.org/10.1007/978-3-540-87608-3_14.
L. Zhao and M. Müller. Using artificial boundaries in the game of Go. In J. van den Herik, X. Xu, Z. Ma, and M. Winands, editors, Computer and Games. 6th International Conference, volume 5131 of Lecture Notes in Computer Science, pages 81-91, Beijing, China, 2008. Springer. http://dx.doi.org/10.1007/978-3-540-87608-3_8.
J. Schaeffer, N. Burch, Y. Björnsson, A. Kishimoto, M. Müller, R. Lake, P. Lu, and S. Sutphen. Checkers is solved. Science, 317(5844):1518-1522, 2007.
X. Niu and M. Müller. An open boundary safety-of-territory solver for the game of Go. In J. van den Herik, P. Ciancarini, and H. Donkers, editors, Computer and Games. 5th International Conference, volume 4630 of Lecture Notes in Computer Science, pages 37 - 49, Torino, Italy, 2007. Springer.
A. Botea, M. Müller, and J. Schaeffer. Fast planning with iterative macros. In Twentieth International Joint Conference on Artificial Intelligence (IJCAI), pages 1828-1833, Hyderabad, India, 2007.
D. Silver, R. Sutton, and M. Müller. Reinforcement learning of local shape in the game of Go. In Twentieth International Joint Conference on Artificial Intelligence (IJCAI), pages 1053-1058, Hyderabad, India, 2007.
K. Yoshizoe, A. Kishimoto, and M. Müller. Lambda depth-first proof number search and its application to Go. In Twentieth International Joint Conference on Artificial Intelligence (IJCAI), pages 2404-2409, Hyderabad, India, 2007.
S. Gelly and D. Silver. Combining online and offline knowledge in UCT. In Z. Ghahramani (ed.), ICML 2007, pages 273-280.
R. Sutton, A. Koop, and D. Silver. On the role of tracking in stationary environments. In Z. Ghahramani (ed.), ICML 2007, pages 871-878.
S. Soeda, K. Yoshizoe, A. Kishimoto, T. Kaneko, T. Tanaka, and M. Müller. Lambda search based on proof and disproof numbers. Information Processing Society of Japan (IPSJ) Journal, 48(11):3455-3462, 2007. In Japanese.
A. Botea. Improving AI Planning and Search with Automatic Abstraction. PhD thesis, University of Alberta, 2006.
X. Niu, A. Kishimoto, and M. Müller. Recognizing seki in computer Go. In J. van den Herik, S.-C. Hsu, T.-s. Hsu, and H. Donkers, editors, Advances in Computer Games. 11th International Conference, volume 4250 of Lecture Notes in Computer Science, pages 88 - 103. Springer, 2006.
L. Zhao and M. Müller. Solving probabilistic combinatorial games. In J. van den Herik, S.-C. Hsu, T.-s. Hsu, and H. Donkers, editors, Advances in Computer Games. 11th International Conference, volume 4250 of Lecture Notes in Computer Science, pages 225 - 238. Springer, 2006.
A. Kishimoto. Correct and Efficient Search Algorithms in the Presence of Repetitions. PhD thesis, University of Alberta, 2005.
A. Kishimoto and M. Müller. A solution to the GHI problem for depth-first proof-number search. Information Sciences, 175(4):296-314, 2005. DOI: 10.1016/j.ins.2004.04.012
A. Botea, M. Enzenberger, M. Müller, and J. Schaeffer. Macro-FF: Improving AI planning with automatically learned macro-operators. Journal of Artificial Intelligence Research, 24:581-621, 2005.
A. Botea, M. Müller, and J. Schaeffer. Learning partial-order macros from solutions. In S. Biundo, K. Myers, and K. Rajan, editors, ICAPS 2005. Proceedings of the 15th International Conference on Automated Planning and Scheduling, pages 231-240, Monterey, California, 2005.
A. Kishimoto and M. 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.
Erratum: On the final page, "move D6 in R2 makes half an eye"
should read: "move D6 in R2 makes one eye".
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.
J. Schaeffer, Y. Björnsson, N. Burch, A. Kishimoto, M. Müller, R. Lake, P. Lu, and S. Sutphen. Solving Checkers. In International Joint Conference on Artificial Intelligence (IJCAI), pages 292-297, 2005. Distinguished paper award
A. Botea, M. Enzenberger, M. Müller, and J. Schaeffer. Macro-FF. In booklet of the International Planning Competition (IPC-4), 2004.
M. Müller. Go-related research at the University of Alberta. In T. Ito and T. Nakamura, editors, The 9th Game Programming Workshop in Japan 2004, pages 22-23, Japan, 2004. IPSJ SIG-GI (Special Interest Group on Game Informatics). Extended abstract.
J. Zhou and M. Müller. Solving systems of difference constraints incrementally with bidirectional search. Algorithmica, 39(3):255-274, 2004.
A. Botea, M. Müller, and J. Schaeffer. Near optimal hierarchical path-finding. Journal of Game Development, 1(1):7-28, 2004.
X. Niu and M. Müller. An improved safety solver for computer Go. In J. van den Herik, Y. Björnsson, and N. Netanyahu, editors, Computers and Games: 4th International Conference, CG 2004, volume 3846 of Lecture Notes in Computer Science, pages 97-112, Ramat-Gan, Israel, 2006. Springer.
M. Müller and Z. Li. Locally informed global search for sums of combinatorial games. In J. van den Herik, Y. Björnsson, and N. Netanyahu, editors, Computers and Games: 4th International Conference, CG 2004, volume 3846 of Lecture Notes in Computer Science, pages 273-284, Ramat-Gan, Israel, 2006. Springer.
A. Kishimoto and M. Müller. A general solution to the graph history interaction problem. In Nineteenth National Conference on Artificial Intelligence (AAAI 2004), pages 644-649, San Jose, CA, 2004.
M. Müller, M. Enzenberger, and J. Schaeffer. Temperature discovery search. In Nineteenth National Conference on Artificial Intelligence (AAAI 2004), pages 658-663, San Jose, CA, 2004.
L. Zhao and M. Müller. Game-SAT: A preliminary report. In Seventh International Conference on Theory and Applications of Satisfiability Testing (SAT 2004), pages 357-362, Vancouver, Canada, 2004.
A. Botea, M. Müller, and J. Schaeffer. Using component abstraction for automatic generation of macro-actions. In S. Zilberstein, J. Koehler, and S. Koenig, editors, ICAPS 2004. Proceedings of the 14th International Conference on Automated Planning and Scheduling, pages 181-190, Whistler, Canada, 2004.
A. Kishimoto and M. Müller. Df-pn in Go: an application to the one-eye problem. In J. van den Herik, H. Iida, and E. Heinz, editors, Advances in Computer Games 10, pages 125 - 141. Kluwer, 2004.
X. Niu. Recognizing safe territories and stones in computer Go. Master's thesis, University of Alberta, 2004.
L. Zhao. Tackling Post's correspondence problem. 22 pages. Accepted 2/2004 for Journal of Experimental Algorithmics but still not published...
Jonathan Schaeffer, Martin Müller, and Yngvi Björnsson, editors. Computers and Games, Third International Conference, CG 2002, Edmonton, Canada, July 25-27, 2002, Revised Papers, volume 2883 of Lecture Notes in Computer Science. Springer, 2003.
J. Zhou and M. Müller. Depth-first discovery algorithm for incremental topological sorting of directed acyclic graphs. Information Processing Letters, 88(4):195-200, 2003.
J. Zhou. Incremental search algorithms. Master's thesis, University of Alberta, 2003.
M. Müller.
Conditional combinatorial games, and their application to analyzing
capturing races in Go.
Information Sciences, 154(3-4):189-202, 2003.
Erratum: Fig. 1 shows three Nim heaps with 6, 4 and 3 pebbles.
The size 6 heap should be size 5 to be consistent with the text.
M. Müller. Proof-set search. In J. Schaeffer, M. Müller, and Y. Björnsson, editors, Computers and Games 2002, number 2883 in Lecture Notes in Computer Science, pages 88-107. Springer Verlag, 2003.
A. Botea, M. Müller, and J. Schaeffer. Using abstraction for planning in Sokoban. In J. Schaeffer, M. Müller, and Y. Björnsson, editors, Computers and Games 2002, number 2883 in Lecture Notes in Computer Science, pages 360-375. Springer Verlag, 2003.
A. Botea, M. Müller, and J. Schaeffer. Extending PDDL for hierarchical planning and topological abstraction. In iCAPS workshop on PDDL, pages 25-32, 2003.
A. Botea. Reducing planning complexity with topological abstraction. Proceedings of the International Conference on Automated Planning & Scheduling (ICAPS-03) Doctoral Consortium, Trento, Italy, 2003.
L. Zhao. Tackling Post's correspondence problem. In J. Schaeffer, M. Müller, and Y. Björnsson, editors, Computers and Games 2002, number 2883 in Lecture Notes in Computer Science, pages 326-344. Springer Verlag, 2003.
A. Kishimoto and M. Müller. A solution to the GHI problem for depth-first proof-number search. In Proceedings of the 7th Joint Conference on Information Sciences JCIS 2003, pages 489 - 492, 2003.
A. Botea. Using abstraction for heuristic search and planning. In S. Koenig and R. Holte, editors, 5th International Symposium on Abstraction, Reformulation, and Approximation, number 2371 in Lecture Notes in Computer Science, pages 326-327. Springer Verlag, 2002.
N. Bullock. Domineering: Solving large combinatorial search spaces. ICGA Journal, 25(2):67-84, 2002.
N. Bullock. Domineering: Solving large combinatorial search spaces. Master's thesis, University of Alberta, 2002.
M. Müller. Counting the score: Position evaluation in computer Go. ICGA Journal, 25(4):219-228, 2002.
M. Müller. A generalized framework for analyzing capturing races in Go. In Proceedings of Sixth Joint Conference on Information Sciences (JCIS 2002), pages 469-472, 2002.
M. Müller. Multicriteria evaluation in computer game-playing, and its relation to AI planning. In B. Drabble, J. Koehler, and J. Refanidis, editors, Proceedings of Sixth International Conference on AI Planning & Scheduling (AIPS-2002) Workshop on Planning and Scheduling using Multiple Criteria, pages 1-6, Toulouse, France, 2002.
M. Müller and T. Tegos. Experiments in Computer Amazons. In R. Nowakowski, editor, More Games of No Chance, pages 243-260. Cambridge University Press, 2002.
T. Tegos. Shooting the last arrow. Master's thesis, University of Alberta, 2002.
L. Zhao. Solving and creating difficult instances of Post's correspondence problem. Master's thesis, University of Alberta, 2002.
M. Müller. Computer Go. Artificial Intelligence, 134(1-2):145-179, 2002. (preprint)
M. Müller. Solving 5x5 Amazons. In The 6th Game Programming Workshop (GPW 2001), number 14 in IPSJ Symposium Series Vol.2001, pages 64-71, Hakone (Japan), 2001.
M. Müller.
Proof Set Search. Revised and improved version of previous report listed below.
Technical report, University of Alberta TR01-09. 23 pages.
Note: this report is superseded by the Computers and Games 2002 paper above.
M. Müller. Global and local game tree search. Information Sciences, 135(3-4):187-206, 2001.
M. Müller. Review: Computer Go 1984 - 2000. In T. Marsland and I. Frank, editors, Computers and Games 2000, number 2063 in Lecture Notes in Computer Science, pages 426-435. Springer Verlag, 2001.
M. Müller. Partial Order Bounding: A new Approach to Evaluation in Game Tree Search. Artificial Intelligence Journal, 129(1-2), 279-311, 2001. (preprint)
M. Müller. Generalized Thermography: A new approach to evaluation in computer Go. In J. van den Herik and H. Iida, editors, Games in AI Research, pages 203-219, Maastricht 2000, Universiteit Maastricht. First published in Iida, H. (Ed.), Proceedings IJCAI-97 Workshop on Using Games as an Experimental Testbed for AI Research, pages 41-49, Nagoya, 1997.
M. Müller. Not like other games - why tree search in Go is different. In Proceedings of Fifth Joint Conference on Information Sciences (JCIS 2000), pages 974-977, 2000. Extended abstract, invited paper for special session on Heuristic Search and Computer Game Playing. (abstract)
H. Iida and M. Müller. Report on the Second Open Computer-Amazons Championship. ICGA Journal Vol.23 No.1, March 2000.
M. 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. (Abstract)
M. Müller. Race to capture: Analyzing semeai in Go. In Game Programming Workshop in Japan '99, volume 99(14) of IPSJ Symposium Series, pages 61-68, 1999. (Abstract)
M. Müller. Computer Go: A research agenda. ICCA Journal, 22(2):104-112, 1999. A version of the 1998 Computers and Games paper adapted for readers with background in games other than Go. (Abstract)
M. Müller.
Proof-set search.
Technical Report TR-99-20, Electrotechnical Laboratory, Tsukuba,
Japan, 1999.
Note: this report is superseded by the Computers and Games 2002 paper above.
M. Müller.
Partial order bounding: Using partial order evaluation in game tree
search.
Technical Report TR-99-12, Electrotechnical Laboratory, Tsukuba,
Japan, 1999.
Note: this report is superseded by the AI Journal paper above.
M. Müller. Partial Order Evaluation in Game Tree Search, and its Application to Analyzing Semeai in the Game of Go. In Workshop on Search Techniques for Problem Solving Under Uncertainty and Incomplete Information, W. Zhang and S. Koenig, Cochairs, AAAI 1999 Spring Symposium Series, 101--106, AAAI, 1999.
N. Sanechika, M. Tajima, and M. Müller. Observable definitions of fuseki concepts (extended abstract, in Japanese). In Game Programming Workshop in Japan '99, volume 99(14) of IPSJ Symposium Series, pages 117-120, 1999. (English abstract)
M. Müller. Computer Go: A research agenda. In J. van den Herik and H. Iida, editors, Computers and Games, number 1558 in Lecture Notes in Computer Science, pages 252-264. Springer Verlag, 1998. (abstract)
M. Müller. Generalized thermography: A new approach to evaluation in computer Go. In H. Iida, editor, IJCAI-97 Workshop on Using Games as an Experimental Testbed for AI Research, pages 41-49, Nagoya, 1997. Proceedings published as a book Games in AI Research. (abstract)
M. Müller. Playing it safe: Recognizing secure territories in computer Go by using static rules and search. In H. Matsubara, editor, Game Programming Workshop in Japan '97, pages 80-86, Computer Shogi Association, Tokyo, Japan, 1997. (abstract)
M. Müller and R. Gasser. Experiments in computer Go endgames. In R. Nowakowski, editor, Games of No Chance, pages 273-284. Cambridge University Press, 1996. (abstract)
M. Müller, E. Berlekamp, and B. Spight. Generalized thermography: Algorithms, implementation, and application to Go endgames. Technical Report 96-030, ICSI Berkeley, 1996. (abstract, Part1: Text, Part2: Examples)
D. Fotland, M. Müller, and B. Wilcox. An evening with the computer Go programmers: David Fotland, Martin Müller, Bruce Wilcox speak at the San Francisco Go club. Videotape, American Ing Goe, 1996.
M. Müller. Computer Go as a Sum of Local Games: An Application of Combinatorial Game Theory. PhD thesis, ETH Zürich, 1995. Diss. ETH Nr. 11.006.
M. Müller. Game theories and computer Go. In Proc. of the Go and Computer Science Workshop (GCSW'93), Sophia-Antipolis, 1993. INRIA. (abstract and overview)
A. Kierulf, R. Gasser, P. Geiser, M. Müller, and J. Nievergelt. Every interactive system evolves into hyperspace: The case of the Smart Game Board. In H. Maurer, editor, Proc. Hypertext/Hypermedia 1991, pages 174-180, New York, 1991. Springer Verlag. (abstract)
M. Müller. Pattern matching in Explorer. Extended abstract. In Proceedings of the Game Playing System Workshop, pages 1-3, Tokyo, Japan, 1991. ICOT. (abstract)
M. Müller. Measuring the performance of Go programs. In International Go Congress, Beijing, 1991. (abstract)
M. Müller. 1990 International Computer Go Congress. Computer Go, 15:3-5, 1991. A tournament report. (Computer Go No. 15)
M. Müller. The Smart Game Board as a tool for game programmers. In D.N.L. Levy and D.F. Beal, editors, Heuristic Programming in Artificial Intelligence 2, pages 217-231. Ellis Horwood, London, 1990. (abstract)
K. Chen, A. Kierulf, M. Müller, and J. Nievergelt. The Design and Evolution of Go Explorer. In T. A. Marsland and J. Schaeffer, editors, Computers, Chess, and Cognition, pages 271-285. Springer Verlag, New York, 1990.
M. Müller. The 1990 European summer tournaments. Computer Go, 14:6-7, 1990. A tournament report. (Computer Go No. 14)
M. Müller. Eine Theoretische Basis zur Programmierung von Go. (A theoretical basis for programming Go.) In German. Diplomarbeit, Technische Universität Graz, 1989.
M. Müller. 1989 European Computer Go Championship. Computer Go, 11:8-9, 1989. A tournament report. (Computer Go No. 11)