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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A priori knowledge includes knowledge of ‘realistic’ or ‘natural’ elements. This can help when adapting, as some changes need not be explicitly explained, such as the trivial example of player opponents that increase in toughness as they increase in size. A priori can also refer to game design patterns, existing conventions which somewhat binds developers to the forms of previous work in their chosen genre.
- 2.
With a non-rational learning human player at the core of gameplay (who may display high choice variance, i.e. infer different predicates based on the same observations), game processes are usually strictly non-Markovian; however they can still be given Markovian representations as a simplifying assumption.
- 3.
Although continuous systems are constrained to have finite duration of input times, they may have infinite number of inputs defined as vector field maps from an input manifold. This permits a model consistent with the player’s point of view, which is an important part of creating psychologically relevant models.
- 4.
This is a rare occasion when a magic square becomes a Magic Circle (in the sense of Huizinga, not Yang Hui)!.
References
Bateman, C., Boon, R.: 21st Century Game Design, vol. 1. Charles River Media, London (2005)
Bateman, C., Lowenhaupt, R., Nacke, L.: Player typology in theory and practice. In: Digital Games Research Association conference, Utrecht, Netherlands (2011)
Björk, S., Holopainen, J.: Patterns in Game Design. Charles River Media, Hingham (2005)
Breining, S., Kriegel, H.P., Schubert, M., Zufle, A.: Action sequence mining. In: Croonenborghs, T., Driessens, K., Missura, O. (eds.) Second International Workshop on Machine Learning and Data Mining in Games, at European Conference on Machine Learning, Athens, Greece (2011)
Caillois, R.: Man, Play, and Games. Free Press of Glencoe, New York (1961)
Chanel, G., Rebetez, C., Bétrancourt, M., Pun, T.: Emotion assessment from physiological signals for adaptation of game difficulty. IEEE Trans. Syst. Man Cybern. Part A Syst. Hum. 41, 1052–1063 (2011)
Cowley, B., Charles, D., Black, M., Hickey, R.: User-system-experience model for user centered design in computer games. In: Wade, V.P., Ashman, H., Smyth, B. (eds.) AH 2006. LNCS, vol. 4018, pp. 419–424. Springer, Heidelberg (2006). https://doi.org/10.1007/11768012_62
Cowley, B., Charles, D., Black, M., Hickey, R.: Toward an understanding of flow in video games. Comput. Entertain. 6(2), 1–27 (2008)
Cowley, B., Charles, D., Black, M., Hickey, R.: Real-time rule-based classification of player types in computer games. User Model. User-Adapt. Interact. 23(5), 489–526 (2012). https://doi.org/10.1007/s11257-012-9126-z
Cowley, B., Charles, D.: Behavlets: a method for practical player modelling using psychology-based player traits and domain specific features. User Model. User-Adapt. Interact. 26(2), 257–306 (2016)
Cowley, B.U.: How to advance general game playing artificial intelligence by player modelling. arXiv 1606.00401, June 2016
Cowley, B.U., Charles, D.: Adaptive artificial intelligence in games: issues, requirements, and a solution through Behavlets-based general player modelling. arXiv 1607.05028, July 2016
Cowley, B.U., Charles, D.: Short literature review for a general player model based on Behavlets. arXiv 1603.06996, 7 March 2016
Cowley, B.U., Charles, D.: Utility of a Behavlets approach to a decision theoretic predictive player model. arXiv 1603.08973, March 2016
Crowley, K.: Flexible strategy use in young children’s tic-tac-toe. Cogn. Sci. 17(4), 531–561 (1993)
Espejo, R., Harnden, R.: The Viable System Model: Interpretations and Applications of Stafford Beer’s VSM. Wiley, New York (1989)
Gmytrasiewicz, P.J., Lisetti, C.L.: Modeling users’ emotions during interactive entertainment sessions (2000)
Grünvogel, S.: Formal models and game design. Games Stud. 5(1), 1–9 (2005)
Huizinga, J.: Homo Ludens: A Study of the Play-element of Culture. Routledge, London (1949)
Hunicke, R., LeBlanc, M., Zubek, R.: MDA: a formal approach to game design and game research. In: Proceedings of the Challenges in Game AI Workshop. AAAI Press, Stanford University in Palo Alto, CA (2004)
Järvinen, A.: Games Without Frontiers: Methods for Game Studies and Design. VDM Verlag, Copenhagen (2009)
Koster, R.: A Theory of Fun for Game Design. Paraglyph Press, Scottsdale (2005)
Malone, T.W.: What makes things fun to learn? Heuristics for designing instructional computer games. In: SIGSMALL 1980: Proceedings of the 3rd ACM SIGSMALL Symposium and the First SIGPC Symposium on Small Systems, Palo Alto, California, United States, pp. 162–169. ACM Press (1980)
Malone, T.W.: What makes computer games fun? [for education]. BYTE 6(12), 258–277 (1981)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Rauterberg, M.: About a framework for information and information processing of learning systems. In: Falkenberg, E.D., Hesse, W., Olivé, A. (eds.) Information System Concepts. IAICT, pp. 54–69. Springer, Boston, MA (1995). https://doi.org/10.1007/978-0-387-34870-4_7
Salen, K., Zimmerman, E.: Rules of Play: Game Design Fundamentals, vol. 1. MIT, London (2004)
Sicart, M.: Defining game mechanics. Games Stud. 8(2) (2008)
Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Steinkuehler, C., Duncan, S.: Scientific habits of mind in virtual worlds. J. Sci. Educ. Technol. 17(6), 530–543 (2008)
Swalwell, M., Wilson, J., Kücklich, J.: Forbidden pleasures - cheating in computer games. In: The Pleasures of Computer Gaming: Essays on Cultural History, Theory and Aesthetics. McFarland & Co., Jefferson, N.C. (2008)
Tabuada, P., Pappas, G.J., Lima, P.: Compositional abstractions of hybrid control systems. Discret. Event Dyn. Syst. 14(2), 203–238 (2004)
Von Neuman, J., Morgenstern, O.: Theory of Games and Economic Behavior. Wiley, New York (1944)
Walters, R.: Categories and Computer Science. Cambridge University Press, Cambridge (1991)
Yannakakis, G.N.: Game AI revisited. In: Proceedings of the 9th Conference on Computing Frontiers, CF 2012, pp. 285–292. ACM, New York (2012)
Yannakakis, G.N., Togelius, J.: A panorama of artificial and computational intelligence in games. IEEE Trans. Comput. Intell. AI Games 7(4), 317–335 (2015). https://doi.org/10.1109/TCIAIG.2014.2339221
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cowley, B.U. (2020). Generalised Player Modelling: Why Artificial Intelligence in Games Should Incorporate Meaning, with a Formalism for so Doing. In: Fang, X. (eds) HCI in Games. HCII 2020. Lecture Notes in Computer Science(), vol 12211. Springer, Cham. https://doi.org/10.1007/978-3-030-50164-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-50164-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50163-1
Online ISBN: 978-3-030-50164-8
eBook Packages: Computer ScienceComputer Science (R0)