ABSTRACT. We present an ongoing research on a probabilistic extension of action language BC+. Just like BC+ is defined as a high-level notation of answer set programs for describing transition systems, the proposed language, which we call pBC+, is defined as a high-level notation of lpmln programs - a probabilistic extension of answer set programs.

As preliminary results accomplished, we illustrate how probabilistic reasoning about transition systems, such as prediction, postdiction, and planning problems, as well as probabilistic diagnosis for dynamic domains, can be modeled in pBC+ and computed using an implementation of LP^MLN.

For future work, we plan to develop a compiler that automatically translates pBC+ description into LP^MLN programs, as well as parameter learning in probabilistic action domains through lpmln weight learning. We will work on defining useful extensions of pBC+ to facilitate hypothetical/counterfactual reasoning. We will also find real-world applications, possibly in robotic domains, to empirically study the performance of this approach to probabilistic reasoning in action domains.