Generalised Player Modelling: Why Artificial Intelligence in Games Should Incorporate Meaning, with a Formalism for so Doing. Cowley, B. U. In International Conference on Human-Computer Interaction HCII 2020: HCI in Games, volume 12211, pages 3–22, 2020. jufo-0abstract bibtex General game-playing artificial intelligence (AI) has recently seen important advances due to the various techniques known as ‘deep learning’. However, in terms of human-computer interaction, the advances conceal a major limitation: these algorithms do not incorporate any sense of what human players find meaningful in games.I argue that adaptive game AI will be enhanced by a generalised player model, because games are inherently human artefacts which require some encoding of the human perspective in order to respond naturally to individual players. The player model provides constraints on the adaptive AI, which allow it to encode aspects of what human players find meaningful. I propose that a general player model requires parameters for the subjective experience of play, including: player psychology, game structure, and actions of play. I argue that such a player model would enhance efficiency of per-game solutions, and also support study of game-playing by allowing (within-player) comparison between games, or (within-game) comparison between players (human and AI).Here we detail requirements for functional adaptive AI, arguing from first-principles drawn from games research literature, and propose a formal specification for a generalised player model based on our ‘Behavlets’ method for psychologically-derived player modelling.
@inproceedings{cowley_generalised_2020,
title = {Generalised {Player} {Modelling}: {Why} {Artificial} {Intelligence} in {Games} {Should} {Incorporate} {Meaning}, with a {Formalism} for so {Doing}},
volume = {12211},
copyright = {All rights reserved},
isbn = {978-3-030-50164-8},
abstract = {General game-playing artificial intelligence (AI) has recently seen important advances due to the various techniques known as ‘deep learning’. However, in terms of human-computer interaction, the advances conceal a major limitation: these algorithms do not incorporate any sense of what human players find meaningful in games.I argue that adaptive game AI will be enhanced by a generalised player model, because games are inherently human artefacts which require some encoding of the human perspective in order to respond naturally to individual players. The player model provides constraints on the adaptive AI, which allow it to encode aspects of what human players find meaningful. I propose that a general player model requires parameters for the subjective experience of play, including: player psychology, game structure, and actions of play. I argue that such a player model would enhance efficiency of per-game solutions, and also support study of game-playing by allowing (within-player) comparison between games, or (within-game) comparison between players (human and AI).Here we detail requirements for functional adaptive AI, arguing from first-principles drawn from games research literature, and propose a formal specification for a generalised player model based on our ‘Behavlets’ method for psychologically-derived player modelling.},
language = {English},
booktitle = {International {Conference} on {Human}-{Computer} {Interaction} {HCII} 2020: {HCI} in {Games}},
author = {Cowley, Benjamin Ultan},
year = {2020},
note = {jufo-0},
keywords = {113 Computer and information sciences, 515 Psychology, 6162 Cognitive science},
pages = {3--22},
}
Downloads: 0
{"_id":"pjp9DiyP9ztQ4Eef8","bibbaseid":"cowley-generalisedplayermodellingwhyartificialintelligenceingamesshouldincorporatemeaningwithaformalismforsodoing-2020","authorIDs":["he39nswtJk5wYHxsx","qX9krPRnrAXQAyYP8"],"author_short":["Cowley, B. U."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Generalised Player Modelling: Why Artificial Intelligence in Games Should Incorporate Meaning, with a Formalism for so Doing","volume":"12211","copyright":"All rights reserved","isbn":"978-3-030-50164-8","abstract":"General game-playing artificial intelligence (AI) has recently seen important advances due to the various techniques known as ‘deep learning’. However, in terms of human-computer interaction, the advances conceal a major limitation: these algorithms do not incorporate any sense of what human players find meaningful in games.I argue that adaptive game AI will be enhanced by a generalised player model, because games are inherently human artefacts which require some encoding of the human perspective in order to respond naturally to individual players. The player model provides constraints on the adaptive AI, which allow it to encode aspects of what human players find meaningful. I propose that a general player model requires parameters for the subjective experience of play, including: player psychology, game structure, and actions of play. I argue that such a player model would enhance efficiency of per-game solutions, and also support study of game-playing by allowing (within-player) comparison between games, or (within-game) comparison between players (human and AI).Here we detail requirements for functional adaptive AI, arguing from first-principles drawn from games research literature, and propose a formal specification for a generalised player model based on our ‘Behavlets’ method for psychologically-derived player modelling.","language":"English","booktitle":"International Conference on Human-Computer Interaction HCII 2020: HCI in Games","author":[{"propositions":[],"lastnames":["Cowley"],"firstnames":["Benjamin","Ultan"],"suffixes":[]}],"year":"2020","note":"jufo-0","keywords":"113 Computer and information sciences, 515 Psychology, 6162 Cognitive science","pages":"3–22","bibtex":"@inproceedings{cowley_generalised_2020,\n\ttitle = {Generalised {Player} {Modelling}: {Why} {Artificial} {Intelligence} in {Games} {Should} {Incorporate} {Meaning}, with a {Formalism} for so {Doing}},\n\tvolume = {12211},\n\tcopyright = {All rights reserved},\n\tisbn = {978-3-030-50164-8},\n\tabstract = {General game-playing artificial intelligence (AI) has recently seen important advances due to the various techniques known as ‘deep learning’. However, in terms of human-computer interaction, the advances conceal a major limitation: these algorithms do not incorporate any sense of what human players find meaningful in games.I argue that adaptive game AI will be enhanced by a generalised player model, because games are inherently human artefacts which require some encoding of the human perspective in order to respond naturally to individual players. The player model provides constraints on the adaptive AI, which allow it to encode aspects of what human players find meaningful. I propose that a general player model requires parameters for the subjective experience of play, including: player psychology, game structure, and actions of play. I argue that such a player model would enhance efficiency of per-game solutions, and also support study of game-playing by allowing (within-player) comparison between games, or (within-game) comparison between players (human and AI).Here we detail requirements for functional adaptive AI, arguing from first-principles drawn from games research literature, and propose a formal specification for a generalised player model based on our ‘Behavlets’ method for psychologically-derived player modelling.},\n\tlanguage = {English},\n\tbooktitle = {International {Conference} on {Human}-{Computer} {Interaction} {HCII} 2020: {HCI} in {Games}},\n\tauthor = {Cowley, Benjamin Ultan},\n\tyear = {2020},\n\tnote = {jufo-0},\n\tkeywords = {113 Computer and information sciences, 515 Psychology, 6162 Cognitive science},\n\tpages = {3--22},\n}\n\n","author_short":["Cowley, B. U."],"key":"cowley_generalised_2020","id":"cowley_generalised_2020","bibbaseid":"cowley-generalisedplayermodellingwhyartificialintelligenceingamesshouldincorporatemeaningwithaformalismforsodoing-2020","role":"author","urls":{},"keyword":["113 Computer and information sciences","515 Psychology","6162 Cognitive science"],"metadata":{"authorlinks":{"cowley, b":"https://blogs.helsinki.fi/bcowley/publications/"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/19634/collections/TV78LMMA/items?key=F9XtACoGIqxy1Fi3Cdhh8Bxq&format=bibtex&limit=100","creationDate":"2020-07-23T11:29:13.044Z","downloads":0,"keywords":["113 computer and information sciences","515 psychology","6162 cognitive science"],"search_terms":["generalised","player","modelling","artificial","intelligence","games","incorporate","meaning","formalism","doing","cowley"],"title":"Generalised Player Modelling: Why Artificial Intelligence in Games Should Incorporate Meaning, with a Formalism for so Doing","year":2020,"dataSources":["AQiMfQvX7ga5gRq8M","64t5GHojmyNGvCTor","rt4MrmmGcSWT2Y9t4"]}