History-Dependent Graphical Multiagent Models

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 individualor 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 tocondition on history, thus supporting inference about system dynamics. To evaluate this hGMM representation westudy a voting consensus scenario, where agents on a network attempt to reach a preferred unanimous vote through aprocess of smooth fictitious play. We induce hGMMs and individual behavior models from example traces, showing thatthe former provide better predictions, given limited historyinformation. These hGMMs also provide advantages for answering general inference queries compared to sampling thetrue generative model.

Authors

• Quang Duong
• Michael Wellman
• Satinder Singh
• Yevgeniy Vorobeychik Washington University, St. Louis

Keywords

• Multiagent reasoning
• graphical multiagent models
• agentbased modeling