The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
A STRATEGIC METAGAME PLAYER FOR GENERAL CHESS‐LIKE GAMES
Abstract
This paper introduces METAGAMER, the first program designed within the paradigm of Metagame‐playing (Metagame). This program plays games in the class of symmetric chess‐like games, which includes chess, Chinese chess, checkers, draughts, and Shogi. METAGAMER takes as input the rules of a specific game and analyzes those rules to construct an efficient representation and an evaluation function for that game; they are used by a generic search engine. The strategic analysis performed by METAGAMER relates a set of general knowledge sources to the details of the particular game. Among other properties, this analysis determines the relative value of the different pieces in a given game. Although METAGAMER does not learn from experience, the values resulting from its analysis are qualitatively similar to values used by experts on known games and are sufficient to produce competitive performance the first time METAGAMER plays a new game. Besides being the first Metagame‐playing program, this is the first program to have derived useful piece values directly from analysis of the rules of different games. This paper describes the knowledge implemented in METAGAMER, illustrates the piece values METAGAMER derives for chess and checkers, and discusses experiments with METAGAMER on both existing and newly generated games.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These results bring us a step closer to fulfilling a longstanding ambition of artificial intelligence ( 3 ): a general games playing system that can learn to master any game.”
From A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play (2018) · cites this paper as [3]
Citations
Cites
TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
Tesauro, G. J. (1994) · Neural Computation · doi:10.1162/neco.1994.6.2.215 · Cited by 821
Temporal credit assignment in reinforcement learning
Sutton, R. S. (1984) · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · Cited by 749
Some Studies in Machine Learning Using the Game of Checkers. II—Recent Progress
Samuel, A. L. (1967) · IBM Journal of Research and Development · doi:10.1147/rd.116.0601 · Cited by 700
Competitive Environments Evolve Better Solutions for Complex Tasks
Angeline, P. J., & Pollack, J. B. (1993) · Cited by 263
Preferential semantics for goals
Wellman, M. P., & Doyle, J. (1991) · Cited by 167
A Study of Explanation-Based Methods for Inductive Learning
Flann, N. S., & Dietterich, T. G. (1989) · Machine Learning · doi:10.1023/a:1022652016863 · Cited by 147
Expected-outcome: a general model of static evaluation
Abramson, B. D. (1990) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.44404 · Cited by 131
A pattern classification approach to evaluation function learning
Lee, K.-F., & Mahajan, S. (1988) · Artificial Intelligence · doi:10.1016/0004-3702(88)90076-8 · Cited by 81
Strategy Generation and Evaluation for Meta-Game Playing
Pell, B. (2011) · KI - Künstliche Intelligenz · doi:10.1007/s13218-010-0082-7 · Cited by 73
Self-citationChess as problem solving: the development of a tactics analyzer.
Berliner, H. (1975) · Cited by 63
Research works printed but not linked: 14
- Baum E. B., 1993, Best play for imperfect players and game tree search
- deGrey A.1985.Towards a versatile self‐learning board game program. Final project Tripos in Computer Science University of Cambridge.
- Epstein S., 1989, Heuristic programming in artificial intelligence–the first computer olympiad
- 10.1007/BF00993346 · DOI
- Findler N. V., 1983, Computer game‐playing
- Gambäck B., 1991, Heuristic programming in artificial intelligence 2–the second computer olympiad
- Good I. J., 1968, Machine intelligence 2, 89
- Hunvald H., 1972, Chess: Quotations from the masters
- Levinson R. A., 1993, Distance: towards the unification of chess knowledge, International Computer Chess Association Journal, 16, 123
- Pell B., 1992, Heuristic programming in artificial intelligence 3–the third computer olympiad
- Pell B.1993a.Logic programming for general game playing.InProceedings of ML93 Workshop on Knowledge Compilation and Speedup Learning. Machine Learning Conference Amherst MA. Also appears as University of Cambridge Computer Laboratory Technical Report No. 302.
- Russell S., 1992, Do the right thing
- Schaeffer J., 1991, Heuristic programming in artificial intelligence 2–the second computer olympiad
- Schraudolph N. N., 1994, Advances in Neural Information Processing 6
Cited by
Sorted by citations
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.01815 · Cited by 1,102
“However, these systems are highly tuned to their domain, and cannot be generalised to other problems without significant human effort, while general game-playing systems (12, 25) remain comparatively weak.”
BackgroundSimulation-based approach to general game playing
Finnsson, H., & Björnsson, Y. (2008) · Cited by 237
CadiaPlayer: A Simulation-Based General Game Player
Björnsson, Y., & Finnsson, H. (2009) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2009.2018702 · Cited by 157
Learning Simulation Control in General Game-Playing Agents
Finnsson, H., & Björnsson, Y. (2010) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v24i1.7651 · Cited by 80
General Board Game Playing for Education and Research in Generic AI Game Learning
Konen, W. (2019) · 2019 IEEE Conference on Games (CoG) · doi:10.1109/cig.2019.8848070 · Cited by 26
CADIA-Player : a general game playing agent
Finnsson, H. (2007) · Cited by 25
Simulation-Based General Game Playing
Finnsson, H. (2012) · Opin vísindi (Opin vísindi) · Cited by 23
Piette, É., Stephenson, M., Soemers, D. J. N. J., & Browne, C. (2021) · IEEE Conference on Games (CoG) · doi:10.1109/cog52621.2021.9618990 · Cited by 22
CadiaPlayer: Search-Control Techniques
Finnsson, H., & Björnsson, Y. (2011) · Künstliche Intell. · doi:10.1007/s13218-010-0080-9 · Cited by 20
Knowledge-Based General Game Playing
Haufe, S., Michulke, D., Schiffel, S., & Thielscher, M. (2011) · Künstliche Intell. · doi:10.1007/s13218-010-0073-8 · Cited by 12
Experimental Studies of Integrated Cognitive Systems
Langley, P., & Messina, E. R. (2004) · Cited by 10
Can Monte-Carlo Tree Search learn to sacrifice?
Companez, N., & Aleti, A. (2016) · Journal of Heuristics · doi:10.1007/s10732-016-9320-y · Cited by 9
Automated domain analysis and transfer learning in general game playing
Kuhlmann, G. (2010) · Cited by 8
Kaiser, D. M. (2005) · ACM Southeast Regional Conference (ACMSE) · doi:10.1145/1167350.1167378 · Cited by 7
Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules
Gonzalez, J. J., Cooper, S., & Guzdial, M. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v19i1.27522 · Cited by 6
Plausible Move Generation Using Move Merit Analysis with Cut-Off Thresholds in Shogi
Grimbergen, R. (2001) · Lecture notes in computer science · doi:10.1007/3-540-45579-5_21 · Cited by 6
Project Thyia: A Forever Gameplayer
Gaina, R. D., Lucas, S. M., & Pérez-Liébana, D. (2019) · IEEE Conference on Games (CoG) · doi:10.1109/cig.2019.8848047 · Cited by 7
Kowalski, J., & Kisielewicz, A. (2015) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2015.7257061 · Cited by 5
Definition and properties to assess multi-agent environments as social intelligence testsPreprint
Insa-Cabrera, J., & Hernández‐Orallo, J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.6350 · Cited by 4
Rules for Expectation: Learning to Generate Rules via Social Environment Modeling
Pu, J., Duan, H., Zhao, J., & Long, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3334526 · Cited by 3
Towards a Universal Test of Social Intelligence
Insa-Cabrera, J. (2016) · doi:10.4995/thesis/10251/66080 · Cited by 3
Behavioural Equivalence of Game Descriptions
Zhang, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64984-5_24 · Cited by 3
The Undergraduate Games Corpus: A Dataset for Machine Perception of Interactive Media
Anderson, B. R., & Smith, A. M. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i1.16071 · Cited by 2
A proposal of learning system with fuzzy rules under large environments
Hoshino, Y., & Kamei, K. (2003) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1999.830867 · Cited by 2
Fuzzy group decision making in a competitive situation
Jiang, Y., Harten, V. A. A., & Wegen, V. D. L. (1997) · TU/e Research Portal · Cited by 2
Existence of symmetric metaequilibria and their a-priori probability in metagames
Jiang, Y., van Harten, A., & van der Wegen, L. L. M. (1997) · TU/e Research Portal · Cited by 2
Multi-game playing — A challenge for computational intelligence
Mańdziuk, J., Ong, Y.-S., & Walȩdzik, K. (2013) · IEEE Symposium on Computational Intelligence for Human-like Intelligence (CIHLI) · doi:10.1109/cihli.2013.6613260 · Cited by 1
A Simulation-Based General Game Player
Bj, Y., & Finnsson, H. (2009) · Cited by 1
Metaprogramming Domain Specific Metaprograms
Cazenave, T. (1999) · Lecture notes in computer science · doi:10.1007/3-540-48443-4_21 · Cited by 1
Unsupervised Learning in Metagame
Farr, G. E., & Powell, D. (1999) · Lecture notes in computer science · doi:10.1007/3-540-46695-9_3 · Cited by 1
Pattern Analysis and Analogy in Shogi: Predicting Shogi Moves from Prior Experience
Walczak, S. M., & Grimbergen, R. (2000) · Knowledge and Information Systems · doi:10.1007/s101150050010 · Cited by 1
MAKU: A Code Generator for Bullet Hell Games
Collman, N. (2014) · MacSphere (McMaster University) · doi:10.71548/22697 · Cited by 1
Implementation of a simulation-based General Game Playing agent
Menger, V. (2012) · Utrecht University Repository (Utrecht University)
Plausible Move Generation in Two-player Complete Information Games Using Static Evaluation.
Grimbergen, R., & Matsubara, H. (2001) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.16.55
The Characterization of Chance and Skill in Games
Erdmann, J. (2011) · Common Library Network (Der Gemeinsame Bibliotheksverbund)
Kaiser, D. (2007) · doi:10.25148/etd.fi08081528
(2005) · A K Peters/CRC Press eBooks · doi:10.1201/b10697-18
General Game Playing With State-Independent Communication
Zammit, S., & Thielscher, M. (2023) · Principles of Knowledge Representation and Reasoning · doi:10.24963/kr.2023/69
AutoGT: Automatic Generation of Game Trees for Algorithm Benchmarking
Karwowski, J., Świechowski, M., & Mańdziuk, J. (2025) · IEEE Transactions on Games · doi:10.1109/tg.2025.3566891
Generating Search Knowledge in a Class of Games
Cazenave, T. (2000)
A Toolkit for Developing Programs of Card Games Played on the Internet
Koide, M., & Cheng, J. (2003) · IFIP advances in information and communication technology · doi:10.1007/978-0-387-35660-0_7
Metadata
- Authors
- Pell, B.
- Affiliations
- Ames Research Center (US)
- Corresponding author
- Pell, Barney
- Venue
- Computational Intelligence
- Publisher
- Wiley
- Published
- 1996-02
- Volume
- 12
- Issue
- 1
- Pages
- 177-198
- ISSN
- 0824-7935 (ISSN-L)
- 1467-8640
- OpenAlex
- W2079303600
- Cited by
- 42
- References
- 34
- Citations by year
- 2025: 1 · 2023: 3 · 2021: 3 · 2020: 1 · 2019: 2 · 2018: 1 · 2016: 2 · 2015: 1 · 2014: 2 · 2013: 1 · 2012: 2
- FWCI
- 1.91
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Computational Intelligence (publishedVersion)
- Funders
- University of Cambridge
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- symmetric games, chess, checkers, draught, Chinese chess, shogi
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
