Probabilistic Planning with Risk-Sensitive Criterion


  • Ping Hou New Mexico State University



Markov Decision Process, Utility Theory, Partially Observable Markov Decision Process


While probabilistic planning models have been extensively used by AI and Decision Theoretic communities for planning under uncertainty, the objective to minimize the expected cumulative cost is inappropriate for high-stake planning problems. With this motivation in mind, we revisit the Risk-Sensitive criterion (RS-criterion), where the objective is to find a policy that maximizes the probability that the cumulative cost is within some user-defined cost threshold. The overall scope of this research is to develop efficient and scalable algorithms to optimize the RS-criterion in probabilistic planning problems. In our recent paper (Hou, Yeoh, and Varakantham 2014), we formally defined Risk-Sensitive MDPs (RS-MDPs) and introduced new algorithms for RS-MDPs with non-negative costs. Next, my plan is to develop algorithm for RS-MDPs with negative cost cycles and for Risk-Sensitive POMDPs (RS-POMDPs).




How to Cite

Hou, P. (2015). Probabilistic Planning with Risk-Sensitive Criterion. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1).