Probabilistic Planning with Risk-Sensitive Criterion
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.
@inproceedings{ijcai2016p572,
title = {Probabilistic Planning with Risk-Sensitive Criterion},
author = {Hou, Ping},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {3996--3996},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/572},
}
TY - CPAPER TI - Probabilistic Planning with Risk-Sensitive Criterion AU - Hou, Ping T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 3996 EP - 3996 UR - https://ijcai.org/proceedings/2016/572 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
