Bridging Commonsense Reasoning and Probabilistic Planning via a Probabilistic Action Language

作者: YI WANG , SHIQI ZHANG , JOOHYUNG LEE

DOI: 10.1017/S1471068419000371

关键词:

摘要: To be responsive to dynamically changing real-world environments, an intelligent agent needs perform complex sequential decision-making tasks that are often guided by commonsense knowledge. The previous work on this line of research led the framework called "interleaved reasoning and probabilistic planning" (icorpp), which used P-log for representing commmonsense knowledge Markov Decision Processes (MDPs) or Partially Observable MDPs (POMDPs) planning under uncertainty. A main limitation icorpp is its implementation requires non-trivial engineering efforts bridge formalisms. In paper, we present a unified integrate icorpp's components. particular, extend action language pBC+ express utility, belief states, observation as in POMDP models. Inheriting advantages languages, new provides elaboration tolerant representation reflects idea design system pbcplus2pomdp, compiles description into model can directly processed off-the-shelf solvers compute optimal policy description. Our experiments show it retains while avoiding manual bridging reasoner planner.

参考文章(25)
Nam Tran, Chitta Baral, Encoding probabilistic causal model in probabilistic action language national conference on artificial intelligence. pp. 305- 310 ,(2004)
Shiqi Zhang, Mohan Sridharan, Jeremy L. Wyatt, Mixed Logical Inference and Probabilistic Planning for Robots in Unreliable Worlds IEEE Transactions on Robotics. ,vol. 31, pp. 699- 713 ,(2015) , 10.1109/TRO.2015.2422531
Peter Stone, Shiqi Zhang, CORPP: commonsense reasoning and probabilistic planning, as applied to dialog with a mobile robot national conference on artificial intelligence. pp. 1394- 1400 ,(2015)
Nam Tran, Chitta Baral, Le-Chi Tuan, Reasoning about actions in a probabilistic setting national conference on artificial intelligence. pp. 507- 512 ,(2002) , 10.5555/777092.777171
Enrico Giunchiglia, Joohyung Lee, Vladimir Lifschitz, Norman McCain, Hudson Turner, Nonmonotonic causal theories Artificial Intelligence. ,vol. 153, pp. 49- 104 ,(2004) , 10.1016/J.ARTINT.2002.12.001
Marc Hanheide, Moritz Göbelbecker, Graham S. Horn, Andrzej Pronobis, Kristoffer Sjöö, Alper Aydemir, Patric Jensfelt, Charles Gretton, Richard Dearden, Miroslav Janicek, Hendrik Zender, Geert-Jan Kruijff, Nick Hawes, Jeremy L. Wyatt, Robot task planning and explanation in open and uncertain worlds Artificial Intelligence. ,vol. 247, pp. 119- 150 ,(2017) , 10.1016/J.ARTINT.2015.08.008
CHITTA BARAL, MICHAEL GELFOND, NELSON RUSHTON, Probabilistic reasoning with answer sets Theory and Practice of Logic Programming. ,vol. 9, pp. 57- 144 ,(2009) , 10.1017/S1471068408003645
Leslie Pack Kaelbling, Michael L. Littman, Anthony R. Cassandra, Planning and Acting in Partially Observable Stochastic Domains Artificial Intelligence. ,vol. 101, pp. 99- 134 ,(1998) , 10.1016/S0004-3702(98)00023-X
Vladimir Lifschitz, Fangkai Yang, Joohyung Lee, Action language BC: preliminary report international joint conference on artificial intelligence. pp. 983- 989 ,(2013)
Joseph Babb, Joohyung Lee, Action language BC Journal of Logic and Computation. ,vol. 30, pp. 899- 922 ,(2020) , 10.1093/LOGCOM/EXV062