Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language $p{\cal BC}$+. Issue 3 (23rd May 2021)

• Record Type: Journal Article
• Authors: WANG, YI; LEE, JOOHYUNG
• Is Part Of: Theory and practice of logic programming. Volume 21:Issue 3(2021)
• Page Start: 348
• Page End: 371
• Publication Date: 2021-05-23
• Subjects: answer set programming -- action language -- Markov decision process; Logic programming -- Periodicals; Artificial intelligence -- Computer programs -- Periodicals; Constraint programming (Computer science) -- Periodicals; 005.115
• DOI: 10.1017/S1471068420000472
• Languages: English
• ISSNs: 1471-0684

Abstract

Abstract: We extend probabilistic action language $p{\cal BC}$ + with the notion of utility in decision theory. The semantics of the extended $p{\cal BC}$ + can be defined as a shorthand notation for a decision-theoretic extension of the probabilistic answer set programming language LP MLN . Alternatively, the semantics of $p{\cal BC}$ + can also be defined in terms of Markov decision process (MDP), which in turn allows for representing MDP in a succinct and elaboration tolerant way as well as leveraging an MDP solver to compute a $p{\cal BC}$ + action description. The idea led to the design of the system pbcplus2mdp, which can find an optimal policy of a $p{\cal BC}$ + action description using an MDP solver.