@inproceedings{25,
abstract = {Partially observable Markov decision processes (POMDPs) are the standard models for planning under uncertainty with both finite and infinite horizon. Besides the well-known discounted-sum objective, indefinite-horizon objective (aka Goal-POMDPs) is another classical objective for POMDPs. In this case, given a set of target states and a positive cost for each transition, the optimization objective is to minimize the expected total cost until a target state is reached. In the literature, RTDP-Bel or heuristic search value iteration (HSVI) have been used for solving Goal-POMDPs. Neither of these algorithms has theoretical convergence guarantees, and HSVI may even fail to terminate its trials. We give the following contributions: (1) We discuss the challenges introduced in Goal-POMDPs and illustrate how they prevent the original HSVI from converging. (2) We present a novel algorithm inspired by HSVI, termed Goal-HSVI, and show that our algorithm has convergence guarantees. (3) We show that Goal-HSVI outperforms RTDP-Bel on a set of well-known examples.},
author = {Horák, Karel and Bošanský, Branislav and Chatterjee, Krishnendu},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence},
location = {Stockholm, Sweden},
pages = {4764 -- 4770},
publisher = {IJCAI},
title = {{Goal-HSVI: Heuristic search value iteration for goal-POMDPs}},
doi = {10.24963/ijcai.2018/662},
volume = {2018-July},
year = {2018},
}