Abstract
Interactive computer game logs show the potential for use as replacement for time-consuming supervisory learning processes for embodied, situated agents. However, due to the inherent nature of the data in the logs themselves, for the time being this promise cannot be fulfilled. An unsuccessful attempt to use largely rule-based data mining processes to learn behaviours from game logs led to finding the inherently top-down nature of such processes was fundamentally at odds with the unsupervised bottom-up learning requirement of the problem. Innate issues with game logs toward the goal of unsupervised agent learning are discussed. Possible approaches to the problem subsuming successful applications of various methods in narrower fields are presented for both symbolic and sub-symbolic advocates.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Gorman, B., Frediksson, M., Humphrys, M.: Qase - an integrated api for imitation and general ai research in commercial computer games. In: Proceedings of the IEEE 7th International Conference on Computer Games, CGAMES, pp. 207–214 (2005)
Laird, J.E., van Lent, M.: Human-level ais killer application: Interactive computer games. In: Proceedings of the AAAI Fall Symposium, pp. 80–97. AAAI Press, Menlo Park (2000)
Kuhlmann, G., Knox, W.B., Stone, P.: Know thine enemy: A champion robocup coach agent. In: Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI 2006), pp. 1463–1468 (2006)
Floyd, M.W., Esfandiari, B., Lam, K.: A case based reasoning approach to imitating robocup players. In: Proceedings of the Twenty-First International FLAIRS Conference. AAAI Press, Menlo Park (2008)
Gorman, B., Thurau, C., Bauckhage, C., Humphrys, M.: Bayesian imitation of human behavior in interactive computer games. In: Proceedings of the 18th International Conference on Pattern Recognition, ICPR, vol. 1, pp. 1244–1247 (2006)
Laird, J.E.: It knows what you’re going to do: adding anticipation to a quakebot. In: AGENTS 2001: Proceedings of the fifth international conference on Autonomous agents, pp. 385–392. ACM, New York (2001)
Choi, D., Konik, T., Nejati, N., Park, C., Langley, P.: A believable agent for first-person perspective games. In: Proceedings of the Third Artificial Intelligence and Interactive Digital Entertainment International Conference (AIIDE 2007). AAAI Press, Menlo Park (2007)
Konik, T., Laird, J.: Learning goal hierarchies from structured observations and expert annotations. In: Proceedings of the Fourteenth International Conference on Inductive Logic Programming, pp. 198–215. Springer, Heidelberg (2004)
Nejati, N., Langley, P., Konik, T.: Learning hierarchical task networks by observation. In: Proceedings of the 23 rd International Conference on Machine Learning, vol. 148, pp. 665–672. ACM Press, New York (2006)
Berndt, C.N., Watson, I., Guesgen, H.: Oasis: An open ai standard interface specification to support reasoning, representation and learning in computer games. In: Aha, D., Muñoz-Avila, H., van Lent, M. (eds.) Proceedings of the 2005 IJCAI Workshop on Reasoning, Representation, and Learning in Computer Games, pp. 19–24 (2005)
Freksa, C.: Qualitative spatial reasoning. In: Mark, D.M., Frank, A. (eds.) Cognitive and Linguistic Aspects of Geographic Space, pp. 361–372. Kluwer Academic Publishers, Dordrecht (1991)
Forbus, K.D.: Qualitative reasoning. In: Tucker, J.A. (ed.) The Computer Science and Engineering Handbook, pp. 715–733. CRC Press, Boca Raton (1997)
Forbus, K.D., Mahoney, J.V., Dill, K.: How qualitative spatial reasoning can improve strategy game ais. IEEE Intelligent Systems 17, 25–30 (2002)
Zagal, J., Mateas, M., Fernandez-Vara, C., Hochhalter, B., Lichti, N.: Towards an ontological language for game analysis. In: Proceedings of the Digital Interactive Games Research Association Conference, DiGRA 2005 (2005)
Zhou, S., Ting, S.P.: Qualitative physics for movable objects in mout. In: ANSS 2006: Proceedings of the 39th annual Symposium on Simulation, Washington, DC, USA, pp. 320–325. IEEE Computer Society, Los Alamitos (2006)
Shahar, Y.: A framework for knowledge-based temporal abstraction. Artificial Intelligence 90, 79–133 (1997)
Sacchi, L., Larizza, C., Combi, C., Bellazzi, R.: Data mining with temporal abstractions: learning rules from time series. Data Mining Knowledge Discovery 15, 217–247 (2007)
Pyle, D.: Data Preparation for Data Mining. Morgan Kaufmann, San Francisco (1999)
Brooks, R.A.: Elephants don’t play chess. Robotics and Autonomous Systems 6, 3–15 (1990)
Thurau, C., Bauckhage, C., Sagerer, G.: Combining self organizing maps and multilayer perceptrons to learn bot-behavior for a commercial game. In: Proceedings of GAME-ON 2003, pp. 119–123 (2003)
Thurau, C., Paczian, T., Bauckhage, C.: Is bayesian imitation learning the route to believable gamebots? In: GAME-ON North America, pp. 3–9 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sheehan, M., Watson, I. (2008). On the Usefulness of Interactive Computer Game Logs for Agent Modelling. In: Ho, TB., Zhou, ZH. (eds) PRICAI 2008: Trends in Artificial Intelligence. PRICAI 2008. Lecture Notes in Computer Science(), vol 5351. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89197-0_107
Download citation
DOI: https://doi.org/10.1007/978-3-540-89197-0_107
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89196-3
Online ISBN: 978-3-540-89197-0
eBook Packages: Computer ScienceComputer Science (R0)