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
Flagged first, then by citations
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
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
