Machine Learning-based Game Playing System

A Machine Learning-based Game Playing System is a machine learning-based system that is a game playing system.

• Context:
  • It can solve a ML-based Game Playing Task (by implementing an ML-based game playing algorithm).
  • It can range from being a ML-based Specialized Game Playing System to being a ML-based General Game Playing System.
  • It can range from being an ML-based Two-Player Perfect-Information Game Playing System to being an ML-based Multi-Player Perfect-Information Game Playing System.
  • It can range from being an ML-based Perfect-Information Game Playing System to being an ML-based Imperfect-Information Game Playing System.
• Example(s):
  • an ML-based Tic-Tac-Toe Playing System such as: Michie's Tic-Tac-Toe Game Playing System;
  • an ML-based Backgammon Playing System such as: NeuroGammon or TD-Gammon;
  • an ML-based Checkers Playing System such as: Samuel's Checkers Player;
  • an ML-based Chess Playing System such as:
    • Deep Blue Chess Playing System.
    • AlphaGo Zero Chess Playing System,
    • Leela Chess Zero Game Playing System,
    • Stockfish Chess Playing System;
  • an ML-based Poker Playing System;
  • an ML-based Bridge Playing System.
  • …
• Counter Example(s):
  • a Heuristic Rule-based Game Playing System.
• See: Game Playing Machine, Reinforment Learning, Game-Playing AI Agent, Symbolic Artificial Intelligence, Knowledge Extraction from Games (KEG), Player Modeling, Monte Carlo Tree Search, Temporal Difference Learning, Computer Olympiad.

---

---

References

2017

• (Johannes Furnkranz, 2017) ⇒ Johannes Furnkranz. (2017). "Machine Learning and Game Playing". In: (Sammut & Webb, 2017). DOI:10.1007/978-1-4899-7687-1_509
  • QUOTE: Game playing is a major application area for research in artificial intelligence in general (Schaeffer and van den Herik 2002) and for machine learning in particular (Furnkranz and Kubat 2001). Traditionally, the field is concerned with learning in strategy games such as tic-tac-toe (Michie 1963), checkers (Samuel’s checkers player), backgammon (TD-Gammon), chess (Baxter et al. 2000; Bjornsson and Marsland 2003; Donninger and Lorenz 2006; Sadikov and Bratko 2006), Go (Silver et al. 2016), Othello (Buro 2002), poker (Billings et al. 2002), or bridge (Amit and Markovitch 2006). However, recently computer and video games have received increased attention (Laird and van Lent 2001; Spronck et al. 2006; Ponsen et al. 2006).

2016

• (Silver et al., 2016) ⇒ 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, and Demis Hassabis (2016). "Mastering The Game Of Go With Deep Neural Networks And Tree Search". Nature. 529: 484–489 DOI:10.1038/nature16961

2006a

• (Donninger & Lorenz, 2006) ⇒ Chrilly Donninger, and Ulf Lorenz (2006). "Innovative Opening-Book Handling". In: van den Herik H.J., Hsu SC., Hsu T., Donkers H.H.L.M.. (eds) Advances in Computer Games. ACG 2005. Lecture Notes in Computer Science, vol 4250. Springer, Berlin, Heidelberg. DOI:10.1007/11922155_1

2006b

• (Sadikov & Bratko, 2006) ⇒ Aleksander Sadikov, and Ivan Bratko (2006). "Learning Long-Term Chess Strategies From Databases". Mach Learn 63(3): 329–340. DOI:10.1007/s10994-006-6747-7

2006c

• (Amit & Markovitch, 2006) ⇒ Asaf Amit, and Shaul Markovitch (2006). "Learning To Bid In Bridge". Mach Learn 63(3):287–327. DOI:10.1007/s10994-006-6225-2

2006d

• (Spronck et al., 2006) ⇒ Pieter Spronck, Marc Ponsen, Ida Sprinkhuizen-Kuyper, and Eric Postma (2006). "Adaptive Game AI With Dynamic Scripting". Mach Learn 63(3):217–248. DOI:10.1007/s10994-006-6205-6

2006e

• (Ponsen et al., 2006) ⇒ Marc Ponsen Hector Munoz-Avila, Pieter Spronck, and David W. Aha.(2006). "Automatically Generating Game Tactics Via Evolutionary Learning". AI Mag 27(3):75–84. DOI:10.1609/aimag.v27i3.1894

2003

• (Bjornsson & Marsland, 2003) ⇒ Yngvi Bjornsson, and T.A.Marsland (2003). “Learning Extension Parameters In Game-Tree Search". Information Sciences, 154(3-4), 95-118. DOI:10.1016/S0020-0255(03)00045-8

2002a

• (Schaeffer & Van den Herik, 2002) ⇒ Jonathan Schaeffer, and H.Jaapvan den Herik (2002). "Chips Challenging Champions: Games, Computers and Artificial Intelligence". North-Holland Publishing, Amsterdam. Reprint of a Special Issue of Artificial Intelligence 134(1–2). ISBN:0-444-50949-6, 978-0-4445-0949-9.
  • QUOTE: One of the earliest dreams of the fledgling field of artificial intelligence (AI) was to build computer programs that could play games as well as or better than the best human players. Despite early optimism in the field, the challenge proved to be surprisingly difficult. However, the 1990s saw amazing progress. Computers are now better than humans in Samuel'scheckers, Othello and Scrabble; are at least as good as the best humans in backgammon and chess; and are rapidly improving at hex, go, poker, and shogi. This book documents the progress made in computers playing games and puzzles. The book is the definitive source for material of high-performance game-playing programs.

2002b

• (Schaeffer & Van den Herik, 2002) ⇒ Jonathan Schaeffer, and H.Jaapvan den Herik (2002). "Games, Computers, and Artificial Intelligence". Artificial Intelligence, 134(1-2), 1-7. [1]
  • QUOTE: The work on computer games has resulted in advances in numerous areas of computing. One could argue that the series of computer-chess tournaments that began in 1970 and continue to this day represents the longest running experiment in computing science history. Research using games has demonstrated the benefits of brute-force search, something that has become a widely accepted tool for a number of search-based applications. Many of the ideas that saw the light of day in game-tree search have been applied to other algorithms. Building world-championship-caliber games programs has demonstrated the cost of constructing high-performance artificial-intelligence systems. Games have been used as experimental test beds for many areas of artificial intelligence.

2002c

• (Buro, 2002) ⇒ Michael Buro (2002). "Improving Heuristic Mini-Max Search By Supervised Learning". Artif Intell 134(1–2):85–99. Special Issue on Games, Computers and Artificial Intelligence. DOI:10.1016/S0004-3702(01)00093-5.

2002d

• (Billings et al., 2002) ⇒ Darse Billings, Aaron Davidson, Jonathan Schaeffer, and Duane Szafron (2002). "The Challenge Of Poker". Artif Intell 134(1–2):201–240. Special Issue on Games, Computers and Artificial Intelligence. DOI:10.1016/s0004-3702(01)00130-8

2001a

• (Furnkranz & Kubat, 2001) ⇒ Johannes Furnkranz, and Miroslav Kubat (eds) (2001). "Machines That Learn To Play Games". Volume 8 of advances in computation: theory and practice. Nova Science Publishers, Huntington. ISBN: 1-59033-021-8, 978-1-5903-3021-0.
  • QUOTE: The mind-set that has dominated the history of computer game playing relies on straightforward exploitation of the available computing power. The fact that a machine can explore millions of variations sooner than the sluggish human can wink an eye has inspired hopes that the mystery of intelligence can be cracked, or at least side-stepped, by sheer force. Decades of the steadily growing strength of computer programs have attested to the soundness of this approach. It is clear that deeper understanding can cut the amount of necessary calculations by orders of magnitude. The papers collected in this volume describe how to instill learning skills in game playing machines. The reader is asked to keep in mind that this is not just about games -- the possibility that the discussed techniques will be used in control systems and in decision support always looms in the background.

2001b

• (Laird & van Lent, 2001) ⇒ John Laird, and Michael van Lent (2001) "Human-Level Ai’s Killer Application: Interactive Computer Games". AI Mag 22(2):15–26. DOI:10.1609/aimag.v22i2.1558

2000

• (Baxter et al., 2000) ⇒ Jonathan Baxter, Andrew Tridgell, and Lex Weaver (2000). "Learning To Play Chess Using Temporal Differences". Machine Learning, 40(3), 243-263. DOI:10.1023/A:1007634325138

1963

• (Michie, 1963) ⇒ Donald Michie (1963). "Experiments On The Mechanization Of Game-Learning Part I. Characterization Of The Model And Its Parameters". The Computer Journal, 6(3), 232-236. DOI:10.1093/comjnl/6.3.232
  • QUOTE: A reason for being interested in games is that they provide a microcosm of intellectual activity in general. Those thought processes which we regard as being specifically human accomplishments-learning from experience, inductive reasoning, argument by analogy, the formation and testing of new hypotheses, and so on -- are brought into play even by simple games of mental skill. The problem of artificial intelligence consists in the reduction of these processes to the elementary operations of arithmetic and logic.

    The present work is concerned with one particular mental activity, that of trial-and-error learning, and the mental task used for studying it is the game of Noughts and Crosses, sometimes known as Tic-tac-toe.

---