Knowledge combination in graphical multiagent models

Quang Duong, Michael P. Wellman, Satinder Singh
Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, PMLR R6:145-152, 2008.

Abstract

A graphical multiagent model (GMM) represents a joint distribution over the behavior of a set of agents. One source of knowledge about agents’ behavior may come from game-theoretic analysis, as captured by several graphical game representations developed in recent years. GMMs generalize this approach to express arbitrary distributions, based on game descriptions or other sources of knowledge bearing on beliefs about agent behavior. To illustrate the flexibility of GMMs, we exhibit game-derived models that allow probabilistic deviation from equilibrium, as well as models based on heuristic action choice. We investigate three different methods of integrating these models into a single model representing the combined knowledge sources. To evaluate the predictive performance of the combined model, we treat as actual outcome the behavior produced by a reinforcement learning process. We find that combining the two knowledge sources, using any of the methods, provides better predictions than either source alone. Among the combination methods, mixing data outperforms the opinion pool and direct update methods investigated in this empirical trial.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR6-duong08a, title = {Knowledge combination in graphical multiagent models}, author = {Duong, Quang and Wellman, Michael P. and Singh, Satinder}, booktitle = {Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence}, pages = {145--152}, year = {2008}, editor = {McAllester, David A. and Myllymäki, Petri}, volume = {R6}, series = {Proceedings of Machine Learning Research}, month = {09--12 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r6/main/assets/duong08a/duong08a.pdf}, url = {https://proceedings.mlr.press/r6/duong08a.html}, abstract = {A graphical multiagent model (GMM) represents a joint distribution over the behavior of a set of agents. One source of knowledge about agents’ behavior may come from game-theoretic analysis, as captured by several graphical game representations developed in recent years. GMMs generalize this approach to express arbitrary distributions, based on game descriptions or other sources of knowledge bearing on beliefs about agent behavior. To illustrate the flexibility of GMMs, we exhibit game-derived models that allow probabilistic deviation from equilibrium, as well as models based on heuristic action choice. We investigate three different methods of integrating these models into a single model representing the combined knowledge sources. To evaluate the predictive performance of the combined model, we treat as actual outcome the behavior produced by a reinforcement learning process. We find that combining the two knowledge sources, using any of the methods, provides better predictions than either source alone. Among the combination methods, mixing data outperforms the opinion pool and direct update methods investigated in this empirical trial.}, note = {Reissued by PMLR on 09 October 2024.} }
Endnote
%0 Conference Paper %T Knowledge combination in graphical multiagent models %A Quang Duong %A Michael P. Wellman %A Satinder Singh %B Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2008 %E David A. McAllester %E Petri Myllymäki %F pmlr-vR6-duong08a %I PMLR %P 145--152 %U https://proceedings.mlr.press/r6/duong08a.html %V R6 %X A graphical multiagent model (GMM) represents a joint distribution over the behavior of a set of agents. One source of knowledge about agents’ behavior may come from game-theoretic analysis, as captured by several graphical game representations developed in recent years. GMMs generalize this approach to express arbitrary distributions, based on game descriptions or other sources of knowledge bearing on beliefs about agent behavior. To illustrate the flexibility of GMMs, we exhibit game-derived models that allow probabilistic deviation from equilibrium, as well as models based on heuristic action choice. We investigate three different methods of integrating these models into a single model representing the combined knowledge sources. To evaluate the predictive performance of the combined model, we treat as actual outcome the behavior produced by a reinforcement learning process. We find that combining the two knowledge sources, using any of the methods, provides better predictions than either source alone. Among the combination methods, mixing data outperforms the opinion pool and direct update methods investigated in this empirical trial. %Z Reissued by PMLR on 09 October 2024.
APA
Duong, Q., Wellman, M.P. & Singh, S.. (2008). Knowledge combination in graphical multiagent models. Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R6:145-152 Available from https://proceedings.mlr.press/r6/duong08a.html. Reissued by PMLR on 09 October 2024.

Related Material