Q Duong, MP Wellman, S Singh, and Y Vorobeychik

Ninth International Conference on Autonomous Agents and Multiagent Systems, pages 1215–1222, May 2010.

Copyright © 2010, IFAAMAS.


A dynamic model of a multiagent system defines a probability distribution over possible system behaviors over time. Alternative representations for such models present tradeoffs in expressive power, and accuracy and cost for inferential tasks of interest. In a history-dependent representation, behavior at a given time is specified as a probabilistic function of some portion of system history. Models may be further distinguished based on whether they specify individual or joint behavior. Joint behavior models are more expressive, but in general grow exponentially in number of agents. Graphical multiagent models (GMMs) provide a more compact representation of joint behavior, when agent interactions exhibit some local structure. We extend GMMs to condition on history, thus supporting inference about system dynamics. To evaluate this hGMM representation we study a voting consensus scenario, where agents on a network attempt to reach a preferred unanimous vote through a process of smooth fictitious play. We induce hGMMs and individual behavior models from example traces, showing that the former provide better predictions, given limited history information. These hGMMs also provide advantages for answering general inference queries compared to sampling the true generative model.