A STRATEGIC METAGAME PLAYER FOR GENERAL CHESS‐LIKE GAMES

@article{Pell1996ASM,
  title={A STRATEGIC METAGAME PLAYER FOR GENERAL CHESS‐LIKE GAMES},
  author={Barney Pell},
  journal={Computational Intelligence},
  year={1996},
  volume={12}
}
  • B. Pell
  • Published 1 August 1994
  • Computer Science
  • Computational Intelligence
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… 
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
TLDR
This paper generalizes the AlphaZero approach into a single AlphaZero algorithm that can achieve superhuman performance in many challenging games, and convincingly defeated a world champion program in the games of chess and shogi (Japanese chess), as well as Go.
CADIA-Player : a general game playing agent
TLDR
CADIAPlayer is a GGP agent that uses Monte Carlo rollouts with upper confidence bounds for trees (UCT) as its main search procedure and outperforms naïve Monte Carlo by close to 90% winning ratio on average on a wide range of games, including Checkers and Othello.
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
TLDR
This paper generalises the approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains, and convincingly defeated a world-champion program in each case.
CadiaPlayer: A Simulation-Based General Game Player
TLDR
CadiaPlayer is described, a GGP agent employing a radically different approach: instead of a traditional game-tree search, it uses Monte Carlo simulations for its move decisions and is empirically evaluate different simulation-based approaches on a wide variety of games.
General Board Game Concepts
TLDR
This work proposes to formalise the notion of “game concept”, inspired by terms generally used by game players and designers, and describes concepts for several levels of abstraction, such as the game itself, the moves played, or the states reached.
Generating Search Knowledge in a Class of Games
TLDR
The Introspect system that generates search knowledge for different games is presented and the consequences of different choices that can be made when designing the domain theory are analyzed.
Simulation-Based Approach to General Game Playing
TLDR
This paper introduces and empirically evaluates a new scheme for automatically learning search-control knowledge for guiding the simulation playouts, showing that it offers significant benefits for a variety of games.
Simulation-Based General Game Playing
TLDR
This thesis describes the GGP agent, CADIAPLAYER, and introduces several schemes for automatically learning search guidance based on both statistical and reinforcement learning techniques, and proposes two extensions for MCTS in the context of GGP aimed at improving the effectiveness of the simulations in real time based on in-game statistical feedback.
Differences between Shogi and western Chess from a computational point of view
TLDR
Shogi, Japanese chess, is played by two players on a board of 9 9 squares, attempting ultimately to capture the opponent's king.
General Board Game Playing for Education and Research in Generic AI Game Learning
  • W. Konen
  • Computer Science
    2019 IEEE Conference on Games (CoG)
  • 2019
TLDR
A new general board game (GBG) playing and learning framework that makes a generic TD(λ)-n-tuple agent for the first time available to arbitrary games and helps students to start faster in the area of game learning.
...
...

References

SHOWING 1-10 OF 76 REFERENCES
METAGAME : A New Challenge for Games and Learning
TLDR
The goals, research areas, and general concerns for the idea of Metagame are discussed, which is to write programs which take as input the rules of a set of new games within a pre-specified class, generated by a program which is publicly available.
A game-learning machine
TLDR
Both the test results and the performance of the program con rm the results of the analysis which indicate that consistency search improves game playing performance for su ciently accurate evaluation functions.
REVIVING THE GAME OF CHECKERS
Chinook is the strongest 8 × 8 checkers program around today. Its strength is largely a result of brute-force methods. The program is capable of searching to depths that make it a feared tactician.
Best Play for Imperfect Players and Game Tree Search; part I - theory
TLDR
This work adds a model of uncertainty to the standard evaluation function of game tree search, and describes how to optimally value the tree within the model, and how to eeciently approximate the optimal tree to search.
A Problem-Solver for Making Advice Operational
TLDR
This paper describes an interactive system, called BAR, that operationalizes advice by applying a series of program transformations, which uses means-ends analysis and planning in an abstraction space to identify transformation sequences that might help solve a given problem.
Chess as problem solving: the development of a tactics analyzer.
TLDR
The author considers the fact that chess programs have made almost no gain in strength, as measured on the human scale, in the period 1968 - 1973, as indicative that the popular model of computer chess is near the limits of its exploitability.
A Multi-Strategy Gaming Environment.
TLDR
An interactive environment in which an arbitrary number of human and machine strategies can be pitted against each other, and the authors describe their current work on automatic analysis and synthesis of strategies.
Plans, goals, and search strategies for the selection of a move in chess
TLDR
In the spring of 1970 at the Adriatic resort town of Herzeg-Novi, the strongest speed tournament of all time was held and Bobby Fischer won the double round robin with the amazing score of 19 points (out of a possible 22).
Adaptive Pattern-Oriented Chess
Chess Skill in Man and Machine
TLDR
The heuristic search: An alternative to the alpha-beta minimax procedure and chess thinking: Man versus machine.
...
...