Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp:
E-Artikel
Titel:
Influence-Based Policy Abstraction for Weakly-Coupled Dec-POMDPs
Beteiligte:
Witwicki, Stefan;
Durfee, Edmund
Erschienen:
Association for the Advancement of Artificial Intelligence (AAAI), 2021
Erschienen in:Proceedings of the International Conference on Automated Planning and Scheduling
Sprache:
Nicht zu entscheiden
DOI:
10.1609/icaps.v20i1.13419
ISSN:
2334-0843;
2334-0835
Entstehung:
Anmerkungen:
Beschreibung:
<jats:p>
Decentralized POMDPs are powerful theoretical models for coordinating agents’ decisions in uncertain environments, but the generally-intractable complexity of optimal joint policy construction presents a significant obstacle in applying Dec-POMDPs to problems where many agents face many policy choices. Here, we argue that when most agent choices are independent of other agents’ choices, much of this complexity can be avoided: instead of coordinating full policies, agents need only coordinate policy abstractions that explicitly convey the essential interaction influences. To this end, we develop a novel framework for influence-based policy abstraction for weakly-coupled transition-dependent Dec-POMDP problems that subsumes several existing approaches. In addition to formally characterizing the space of transition-dependent influences, we provide a method for computing optimal and approximately-optimal joint policies. We present an initial empirical analysis, over problems with commonly-studied flavors of transition-dependent influences, that demonstrates the potential computational benefits of influence-based abstraction over state-of-the-art optimal policy search methods.
</jats:p>