---
title: "Probabilistic Planning with Risk-Sensitive Criterion"
authors:
  - "Ping Hou"
doi: ""
url: "https://ijcai.org/proceedings/2016/572"
pdf: "https://ijcai.org/proceedings/2016/0572.pdf"
venue: "Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence"
year: 2016
pages: "3996-3996"
track: ""
keywords:
---

# Probabilistic Planning with Risk-Sensitive Criterion

Ping Hou

*Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence*, pages 3996-3996.

## Abstract

While probabilistic planning have been extensively studied by artificial intelligence 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. By combining goal-directed MDPs and POMDPs with the RS-criterion, the corresponding risk-sensitive probabilistic planning models —Risk-Sensitive MDPs (RS-MDPs) and Risk-Sensitive POMDPs (RS-POMDPs) — can be formalized. The overall scope of this research is to develop efficient and scalable RS-MDP and RS-POMDP algorithms.