Agent Influence and Intelligent Approximation in Multiagent Problems

Allen, Martin; Zilberstein, Shlomo

doi:10.1109/wi-iat.2009.171

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…to work well. Further formalizing the impact of such first-action-modifications may be a promising direction of research, and could lead to a novel notion of influence strength (Allen & Zilberstein, 2009;Oliehoek, Spaan, & Witwicki, 2015b) in multiagent domains.…”

Section: Locality Of Interaction and Value Factorizationmentioning

confidence: 99%

A Sufficient Statistic for Influence in Structured Multiagent Environments

Oliehoek

Witwicki

Kaelbling

2021

jair

View full text Add to dashboard Cite

Making decisions in complex environments is a key challenge in artificial intelligence (AI). Situations involving multiple decision makers are particularly complex, leading to computational intractability of principled solution methods. A body of work in AI has tried to mitigate this problem by trying to distill interaction to its essence: how does the policy of one agent influence another agent? If we can find more compact representations of such influence, this can help us deal with the complexity, for instance by searching the space of influences rather than the space of policies. However, so far these notions of influence have been restricted in their applicability to special cases of interaction. In this paper we formalize influence-based abstraction (IBA), which facilitates the elimination of latent state factors without any loss in value, for a very general class of problems described as factored partially observable stochastic games (fPOSGs). On the one hand, this generalizes existing descriptions of influence, and thus can serve as the foundation for improvements in scalability and other insights in decision making in complex multiagent settings. On the other hand, since the presence of other agents can be seen as a generalization of single agent settings, our formulation of IBA also provides a sufficient statistic for decision making under abstraction for a single agent. We also give a detailed discussion of the relations to such previous works, identifying new insights and interpretations of these approaches. In these ways, this paper deepens our understanding of abstraction in a wide range of sequential decision making settings, providing the basis for new approaches and algorithms for a large class of problems.

show abstract

Section: Locality Of Interaction and Value Factorizationmentioning

confidence: 99%