A Sufficient Statistic for Influence in Structured Multiagent Environments
Name
1907.09278.pdf
Description
Accepted version
Size
732.3 KB
Format
Adobe PDF
Checksum (MD5)
b7ef01153c54ed397e25d3ef565e1983
Author(s)
Oliehoek, Frans
Witwicki, Stefan
Kaelbling, Leslie
Date Issued
2021
Journal
Journal of Artificial Intelligence Research
Publisher
AI Access Foundation
Citation
Oliehoek, Frans, Witwicki, Stefan and Kaelbling, Leslie. 2021. "A Sufficient Statistic for Influence in Structured Multiagent Environments." Journal of Artificial Intelligence Research, 70.
Version
Author's final manuscript
Abstract
© 2021 AI Access Foundation. All rights reserved. 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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1613/JAIR.1.12136
