Probabilistic Knowledge-Based Programs
Lang, Jérôme; Zanuttini, Bruno (2015), Probabilistic Knowledge-Based Programs, in Yang, Qiang; Wooldridge, Michael, Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015), AAAI Press / IJCAI : Palo Alto (USA), p. 1594-1600
TypeCommunication / Conférence
Conference title24th International Joint Conference on Artificial Intelligence (IJCAI 2015)
Conference cityBuenos Aires
Book titleProceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015)
Book authorYang, Qiang; Wooldridge, Michael
Number of pages4429
MetadataShow full item record
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Groupe de Recherche en Informatique, Image et Instrumentation de Caen [GREYC]
Abstract (EN)We introduce Probabilistic Knowledge-Based Programs (PKBPs), a new, compact representation of policies for factored partially observable Markov decision processes. PKBPs use branching conditions such as if the probability of ϕ is larger than p, and many more. While similar in spirit to value-based policies, PKBPs leverage the factored representation for more compactness. They also cope with more general goals than standard state-based rewards, such as pure information-gathering goals. Compactness comes at the price of reactivity, since evaluating branching conditions on-line is not polynomial in general. In this sense, PKBPs are complementary to other representations. Our intended application is as a tool for experts to specify policies in a natural, compact language, then have them verified automatically. We study succinctness and the complexity of verification for PKBPs.
Subjects / KeywordsPlanning; Artificial Intelligence
Showing items related by title and author.
Zanuttini, Bruno; Lang, Jérôme; Saffidine, Abdallah; Schwarzentruber, François (2019) Article accepté pour publication ou publié