General video game playing

John Levine, Clare Bates Congdon, Marc Ebner, Graham Kendall, Simon M. Lucas, Risto Miikkulainen, Tom Schaul, Tommy Thompson

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

One of the grand challenges of AI is to create general intelligence: an agent that can excel at many tasks, not just one. In the area of games, this has given rise to the challenge of General Game Playing (GGP). In GGP, the game (typically a turn-taking board game) is defined declaratively in terms of the logic of the game (what happens when a move is made, how the scoring system works, how the winner is declared, and so on). The AI player then has to work out how to play the game and how to win. In this work, we seek to extend the idea of General Game Playing into the realm of video games, thus forming the area of General Video Game Playing (GVGP). In GVGP, computational agents will be asked to play video games that they have not seen before. At the minimum, the agent will be given the current state of the world and told what actions are applicable. Every game tick the agent will have to decide on its action, and the state will be updated, taking into account the actions of the other agents in the game and the game physics. We envisage running a competition based on GVGP playing, using arcade-style (e.g. similar to Atari 2600) games as our starting point. These games are rich enough to be a formidable challenge to a GVGP agent, without introducing unnecessary complexity. The competition that we envisage could have a number of tracks, based on the form of the state (frame buffer or object model) and whether or not a forward model of action execution is available. We propose that the existing Physical Travelling Salesman (PTSP) software could be extended for our purposes and that a variety of GVGP games could be created in this framework by AI and Games students and other developers. Beyond this, we envisage the development of a Video Game Description Language (VGDL) as a way of concisely specifying video games. For the competition, we see this as being an interesting challenge in terms of deliberative search, machine learning and transfer of existing knowledge into new domains.
LanguageEnglish
Title of host publicationArtificial and Computational Intelligence in Games
Subtitle of host publicationA Follow-up to Dagstuhl Seminar 12191
EditorsSimon M. Lucas, Michael Mateas, Mike Preuss, Pieter Spronck, Julian Togelius
Pages77-84
Number of pages8
DOIs
Publication statusPublished - 30 Nov 2013
EventArtificial and Computational Intelligence in Games - Schloss Dagstuhl – Leibniz Center for Informatics, Wadern, Germany
Duration: 6 May 201211 May 2012
http://www.dagstuhl.de/12191

Publication series

NameDagstuhl Follow-Ups
Publisher Dagstuhl Publishing
ISSN (Print)1868-8977

Conference

ConferenceArtificial and Computational Intelligence in Games
CountryGermany
CityWadern
Period6/05/1211/05/12
Internet address

Fingerprint

Learning systems
Physics
Students

Keywords

  • video games
  • artificial intelligence
  • general game playing
  • general video game playing
  • video game description language
  • artificial general intelligence

Cite this

Levine, J., Bates Congdon, C., Ebner, M., Kendall, G., Lucas, S. M., Miikkulainen, R., ... Thompson, T. (2013). General video game playing. In S. M. Lucas, M. Mateas, M. Preuss, P. Spronck, & J. Togelius (Eds.), Artificial and Computational Intelligence in Games: A Follow-up to Dagstuhl Seminar 12191 (pp. 77-84). (Dagstuhl Follow-Ups). https://doi.org/10.4230/DFU.Vol6.12191.77
Levine, John ; Bates Congdon, Clare ; Ebner, Marc ; Kendall, Graham ; Lucas, Simon M. ; Miikkulainen, Risto ; Schaul, Tom ; Thompson, Tommy. / General video game playing. Artificial and Computational Intelligence in Games: A Follow-up to Dagstuhl Seminar 12191. editor / Simon M. Lucas ; Michael Mateas ; Mike Preuss ; Pieter Spronck ; Julian Togelius. 2013. pp. 77-84 (Dagstuhl Follow-Ups).
@inbook{92023a48ca044638be1260a7f9c1ab89,
title = "General video game playing",
abstract = "One of the grand challenges of AI is to create general intelligence: an agent that can excel at many tasks, not just one. In the area of games, this has given rise to the challenge of General Game Playing (GGP). In GGP, the game (typically a turn-taking board game) is defined declaratively in terms of the logic of the game (what happens when a move is made, how the scoring system works, how the winner is declared, and so on). The AI player then has to work out how to play the game and how to win. In this work, we seek to extend the idea of General Game Playing into the realm of video games, thus forming the area of General Video Game Playing (GVGP). In GVGP, computational agents will be asked to play video games that they have not seen before. At the minimum, the agent will be given the current state of the world and told what actions are applicable. Every game tick the agent will have to decide on its action, and the state will be updated, taking into account the actions of the other agents in the game and the game physics. We envisage running a competition based on GVGP playing, using arcade-style (e.g. similar to Atari 2600) games as our starting point. These games are rich enough to be a formidable challenge to a GVGP agent, without introducing unnecessary complexity. The competition that we envisage could have a number of tracks, based on the form of the state (frame buffer or object model) and whether or not a forward model of action execution is available. We propose that the existing Physical Travelling Salesman (PTSP) software could be extended for our purposes and that a variety of GVGP games could be created in this framework by AI and Games students and other developers. Beyond this, we envisage the development of a Video Game Description Language (VGDL) as a way of concisely specifying video games. For the competition, we see this as being an interesting challenge in terms of deliberative search, machine learning and transfer of existing knowledge into new domains.",
keywords = "video games, artificial intelligence, general game playing, general video game playing, video game description language, artificial general intelligence",
author = "John Levine and {Bates Congdon}, Clare and Marc Ebner and Graham Kendall and Lucas, {Simon M.} and Risto Miikkulainen and Tom Schaul and Tommy Thompson",
year = "2013",
month = "11",
day = "30",
doi = "10.4230/DFU.Vol6.12191.77",
language = "English",
isbn = "9783939897620",
series = "Dagstuhl Follow-Ups",
publisher = "Dagstuhl Publishing",
pages = "77--84",
editor = "Lucas, {Simon M. } and Michael Mateas and Mike Preuss and Pieter Spronck and Julian Togelius",
booktitle = "Artificial and Computational Intelligence in Games",

}

Levine, J, Bates Congdon, C, Ebner, M, Kendall, G, Lucas, SM, Miikkulainen, R, Schaul, T & Thompson, T 2013, General video game playing. in SM Lucas, M Mateas, M Preuss, P Spronck & J Togelius (eds), Artificial and Computational Intelligence in Games: A Follow-up to Dagstuhl Seminar 12191. Dagstuhl Follow-Ups, pp. 77-84, Artificial and Computational Intelligence in Games, Wadern, Germany, 6/05/12. https://doi.org/10.4230/DFU.Vol6.12191.77

General video game playing. / Levine, John; Bates Congdon, Clare; Ebner, Marc; Kendall, Graham; Lucas, Simon M.; Miikkulainen, Risto; Schaul, Tom; Thompson, Tommy.

Artificial and Computational Intelligence in Games: A Follow-up to Dagstuhl Seminar 12191. ed. / Simon M. Lucas; Michael Mateas; Mike Preuss; Pieter Spronck; Julian Togelius. 2013. p. 77-84 (Dagstuhl Follow-Ups).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - General video game playing

AU - Levine, John

AU - Bates Congdon, Clare

AU - Ebner, Marc

AU - Kendall, Graham

AU - Lucas, Simon M.

AU - Miikkulainen, Risto

AU - Schaul, Tom

AU - Thompson, Tommy

PY - 2013/11/30

Y1 - 2013/11/30

N2 - One of the grand challenges of AI is to create general intelligence: an agent that can excel at many tasks, not just one. In the area of games, this has given rise to the challenge of General Game Playing (GGP). In GGP, the game (typically a turn-taking board game) is defined declaratively in terms of the logic of the game (what happens when a move is made, how the scoring system works, how the winner is declared, and so on). The AI player then has to work out how to play the game and how to win. In this work, we seek to extend the idea of General Game Playing into the realm of video games, thus forming the area of General Video Game Playing (GVGP). In GVGP, computational agents will be asked to play video games that they have not seen before. At the minimum, the agent will be given the current state of the world and told what actions are applicable. Every game tick the agent will have to decide on its action, and the state will be updated, taking into account the actions of the other agents in the game and the game physics. We envisage running a competition based on GVGP playing, using arcade-style (e.g. similar to Atari 2600) games as our starting point. These games are rich enough to be a formidable challenge to a GVGP agent, without introducing unnecessary complexity. The competition that we envisage could have a number of tracks, based on the form of the state (frame buffer or object model) and whether or not a forward model of action execution is available. We propose that the existing Physical Travelling Salesman (PTSP) software could be extended for our purposes and that a variety of GVGP games could be created in this framework by AI and Games students and other developers. Beyond this, we envisage the development of a Video Game Description Language (VGDL) as a way of concisely specifying video games. For the competition, we see this as being an interesting challenge in terms of deliberative search, machine learning and transfer of existing knowledge into new domains.

AB - One of the grand challenges of AI is to create general intelligence: an agent that can excel at many tasks, not just one. In the area of games, this has given rise to the challenge of General Game Playing (GGP). In GGP, the game (typically a turn-taking board game) is defined declaratively in terms of the logic of the game (what happens when a move is made, how the scoring system works, how the winner is declared, and so on). The AI player then has to work out how to play the game and how to win. In this work, we seek to extend the idea of General Game Playing into the realm of video games, thus forming the area of General Video Game Playing (GVGP). In GVGP, computational agents will be asked to play video games that they have not seen before. At the minimum, the agent will be given the current state of the world and told what actions are applicable. Every game tick the agent will have to decide on its action, and the state will be updated, taking into account the actions of the other agents in the game and the game physics. We envisage running a competition based on GVGP playing, using arcade-style (e.g. similar to Atari 2600) games as our starting point. These games are rich enough to be a formidable challenge to a GVGP agent, without introducing unnecessary complexity. The competition that we envisage could have a number of tracks, based on the form of the state (frame buffer or object model) and whether or not a forward model of action execution is available. We propose that the existing Physical Travelling Salesman (PTSP) software could be extended for our purposes and that a variety of GVGP games could be created in this framework by AI and Games students and other developers. Beyond this, we envisage the development of a Video Game Description Language (VGDL) as a way of concisely specifying video games. For the competition, we see this as being an interesting challenge in terms of deliberative search, machine learning and transfer of existing knowledge into new domains.

KW - video games

KW - artificial intelligence

KW - general game playing

KW - general video game playing

KW - video game description language

KW - artificial general intelligence

UR - http://www.dagstuhl.de/12191

U2 - 10.4230/DFU.Vol6.12191.77

DO - 10.4230/DFU.Vol6.12191.77

M3 - Chapter

SN - 9783939897620

T3 - Dagstuhl Follow-Ups

SP - 77

EP - 84

BT - Artificial and Computational Intelligence in Games

A2 - Lucas, Simon M.

A2 - Mateas, Michael

A2 - Preuss, Mike

A2 - Spronck, Pieter

A2 - Togelius, Julian

ER -

Levine J, Bates Congdon C, Ebner M, Kendall G, Lucas SM, Miikkulainen R et al. General video game playing. In Lucas SM, Mateas M, Preuss M, Spronck P, Togelius J, editors, Artificial and Computational Intelligence in Games: A Follow-up to Dagstuhl Seminar 12191. 2013. p. 77-84. (Dagstuhl Follow-Ups). https://doi.org/10.4230/DFU.Vol6.12191.77