Knowledge-Based Policies for Qualitative Decentralized POMDPs
Saffidine, Abdallah; Schwarzentruber, François; Zanuttini, Bruno (2018), Knowledge-Based Policies for Qualitative Decentralized POMDPs, 32nd AAAI Conference on Artificial Intelligence, 2018-02, New Orleans, UNITED STATES
TypeCommunication / Conférence
External document linkhttps://hal.archives-ouvertes.fr/hal-01646207
Conference title32nd AAAI Conference on Artificial Intelligence
Conference cityNew Orleans
Conference countryUNITED STATES
MetadataShow full item record
Abstract (EN)Qualitative Decentralized Partially Observable Markov Decision Problems (QDec-POMDPs) constitute a very general class of decision problems. They involve multiple agents, decentralized execution, sequential decision, partial observabil-ity, and uncertainty. Typically, joint policies, which prescribe to each agent an action to take depending on its full history of (local) actions and observations, are huge, which makes it difficult to store them onboard, at execution time, and also hampers the computation of joint plans. We propose and investigate a new representation for joint policies in QDec-POMDPs, which we call Multi-Agent Knowledge-Based Programs (MAKBPs), and which uses epistemic logic for compactly representing conditions on histories. Contrary to standard representations, executing an MAKBP requires reasoning at execution time, but we show that MAKBPs can be exponentially more succinct than any reactive representation.
Showing items related by title and author.
Zanuttini, Bruno; Lang, Jérôme; Saffidine, Abdallah; Schwarzentruber, François (2019) Article accepté pour publication ou publié