The 2014 General Video Game Playing Competition

Diego Perez-Liebana, Spyridon Samothrakis, Julian Togelius, Tom Schaul, Simon M. Lucas, Adrien Couetoux, Jerry Lee, Chong U. Lim, Tommy Thompson

    Research output: Contribution to journalArticle

    Abstract

    This paper presents the framework, rules, games, controllers, and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of general artificial intelligence, as the amount of game-dependent heuristics needs to be severely limited. The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types, and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.

    Original languageEnglish (US)
    Article number7038214
    Pages (from-to)229-243
    Number of pages15
    JournalIEEE Transactions on Computational Intelligence and AI in Games
    Volume8
    Issue number3
    DOIs
    StatePublished - Sep 1 2016

    Fingerprint

    Controllers
    Artificial intelligence
    Mechanics

    Keywords

    • Competitions
    • evolutionary algorithms
    • general video game playing
    • Monte Carlo tree search
    • Real-Time games

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Software
    • Artificial Intelligence
    • Electrical and Electronic Engineering

    Cite this

    Perez-Liebana, D., Samothrakis, S., Togelius, J., Schaul, T., Lucas, S. M., Couetoux, A., ... Thompson, T. (2016). The 2014 General Video Game Playing Competition. IEEE Transactions on Computational Intelligence and AI in Games, 8(3), 229-243. [7038214]. https://doi.org/10.1109/TCIAIG.2015.2402393

    The 2014 General Video Game Playing Competition. / Perez-Liebana, Diego; Samothrakis, Spyridon; Togelius, Julian; Schaul, Tom; Lucas, Simon M.; Couetoux, Adrien; Lee, Jerry; Lim, Chong U.; Thompson, Tommy.

    In: IEEE Transactions on Computational Intelligence and AI in Games, Vol. 8, No. 3, 7038214, 01.09.2016, p. 229-243.

    Research output: Contribution to journalArticle

    Perez-Liebana, D, Samothrakis, S, Togelius, J, Schaul, T, Lucas, SM, Couetoux, A, Lee, J, Lim, CU & Thompson, T 2016, 'The 2014 General Video Game Playing Competition', IEEE Transactions on Computational Intelligence and AI in Games, vol. 8, no. 3, 7038214, pp. 229-243. https://doi.org/10.1109/TCIAIG.2015.2402393
    Perez-Liebana D, Samothrakis S, Togelius J, Schaul T, Lucas SM, Couetoux A et al. The 2014 General Video Game Playing Competition. IEEE Transactions on Computational Intelligence and AI in Games. 2016 Sep 1;8(3):229-243. 7038214. https://doi.org/10.1109/TCIAIG.2015.2402393
    Perez-Liebana, Diego ; Samothrakis, Spyridon ; Togelius, Julian ; Schaul, Tom ; Lucas, Simon M. ; Couetoux, Adrien ; Lee, Jerry ; Lim, Chong U. ; Thompson, Tommy. / The 2014 General Video Game Playing Competition. In: IEEE Transactions on Computational Intelligence and AI in Games. 2016 ; Vol. 8, No. 3. pp. 229-243.
    @article{62ced51faf24406996ea32c5ed80be4e,
    title = "The 2014 General Video Game Playing Competition",
    abstract = "This paper presents the framework, rules, games, controllers, and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of general artificial intelligence, as the amount of game-dependent heuristics needs to be severely limited. The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types, and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.",
    keywords = "Competitions, evolutionary algorithms, general video game playing, Monte Carlo tree search, Real-Time games",
    author = "Diego Perez-Liebana and Spyridon Samothrakis and Julian Togelius and Tom Schaul and Lucas, {Simon M.} and Adrien Couetoux and Jerry Lee and Lim, {Chong U.} and Tommy Thompson",
    year = "2016",
    month = "9",
    day = "1",
    doi = "10.1109/TCIAIG.2015.2402393",
    language = "English (US)",
    volume = "8",
    pages = "229--243",
    journal = "IEEE Transactions on Computational Intelligence and AI in Games",
    issn = "1943-068X",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "3",

    }

    TY - JOUR

    T1 - The 2014 General Video Game Playing Competition

    AU - Perez-Liebana, Diego

    AU - Samothrakis, Spyridon

    AU - Togelius, Julian

    AU - Schaul, Tom

    AU - Lucas, Simon M.

    AU - Couetoux, Adrien

    AU - Lee, Jerry

    AU - Lim, Chong U.

    AU - Thompson, Tommy

    PY - 2016/9/1

    Y1 - 2016/9/1

    N2 - This paper presents the framework, rules, games, controllers, and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of general artificial intelligence, as the amount of game-dependent heuristics needs to be severely limited. The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types, and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.

    AB - This paper presents the framework, rules, games, controllers, and results of the first General Video Game Playing Competition, held at the IEEE Conference on Computational Intelligence and Games in 2014. The competition proposes the challenge of creating controllers for general video game play, where a single agent must be able to play many different games, some of them unknown to the participants at the time of submitting their entries. This test can be seen as an approximation of general artificial intelligence, as the amount of game-dependent heuristics needs to be severely limited. The games employed are stochastic real-time scenarios (where the time budget to provide the next action is measured in milliseconds) with different winning conditions, scoring mechanisms, sprite types, and available actions for the player. It is a responsibility of the agents to discover the mechanics of each game, the requirements to obtain a high score and the requisites to finally achieve victory. This paper describes all controllers submitted to the competition, with an in-depth description of four of them by their authors, including the winner and the runner-up entries of the contest. The paper also analyzes the performance of the different approaches submitted, and finally proposes future tracks for the competition.

    KW - Competitions

    KW - evolutionary algorithms

    KW - general video game playing

    KW - Monte Carlo tree search

    KW - Real-Time games

    UR - http://www.scopus.com/inward/record.url?scp=84988654348&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84988654348&partnerID=8YFLogxK

    U2 - 10.1109/TCIAIG.2015.2402393

    DO - 10.1109/TCIAIG.2015.2402393

    M3 - Article

    AN - SCOPUS:84988654348

    VL - 8

    SP - 229

    EP - 243

    JO - IEEE Transactions on Computational Intelligence and AI in Games

    JF - IEEE Transactions on Computational Intelligence and AI in Games

    SN - 1943-068X

    IS - 3

    M1 - 7038214

    ER -