Expectation optimization with probabilistic guarantees in POMDPs with discounted-sum objectives

K. Chatterjee, A. Elgyütt, P. Novotny, O. Rouillé, in:, IJCAI, 2018, pp. 4692–4699.


Conference Paper | Published | English
Abstract
Partially-observable Markov decision processes (POMDPs) with discounted-sum payoff are a standard framework to model a wide range of problems related to decision making under uncertainty. Traditionally, the goal has been to obtain policies that optimize the expectation of the discounted-sum payoff. A key drawback of the expectation measure is that even low probability events with extreme payoff can significantly affect the expectation, and thus the obtained policies are not necessarily risk-averse. An alternate approach is to optimize the probability that the payoff is above a certain threshold, which allows obtaining risk-averse policies, but ignores optimization of the expectation. We consider the expectation optimization with probabilistic guarantee (EOPG) problem, where the goal is to optimize the expectation ensuring that the payoff is above a given threshold with at least a specified probability. We present several results on the EOPG problem, including the first algorithm to solve it.
Publishing Year
Date Published
2018-07-01
Acknowledgement
This research was supported by the Vienna Science and Technology Fund (WWTF) grant ICT15-003; Austrian Science Fund (FWF): S11407-N23(RiSE/SHiNE);and an ERC Start Grant (279307:Graph Games).
Volume
2018
Page
4692 - 4699
Conference
IJCAI: International Joint Conference on Artificial Intelligence
Conference Location
Stockholm, Sweden
Conference Date
2018-07-13 – 2018-07-19
IST-REx-ID

Cite this

Chatterjee K, Elgyütt A, Novotny P, Rouillé O. Expectation optimization with probabilistic guarantees in POMDPs with discounted-sum objectives. In: Vol 2018. IJCAI; 2018:4692-4699. doi:10.24963/ijcai.2018/652
Chatterjee, K., Elgyütt, A., Novotny, P., & Rouillé, O. (2018). Expectation optimization with probabilistic guarantees in POMDPs with discounted-sum objectives (Vol. 2018, pp. 4692–4699). Presented at the IJCAI: International Joint Conference on Artificial Intelligence, Stockholm, Sweden: IJCAI. https://doi.org/10.24963/ijcai.2018/652
Chatterjee, Krishnendu, Adrian Elgyütt, Petr Novotny, and Owen Rouillé. “Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-Sum Objectives,” 2018:4692–99. IJCAI, 2018. https://doi.org/10.24963/ijcai.2018/652.
K. Chatterjee, A. Elgyütt, P. Novotny, and O. Rouillé, “Expectation optimization with probabilistic guarantees in POMDPs with discounted-sum objectives,” presented at the IJCAI: International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 2018, vol. 2018, pp. 4692–4699.
Chatterjee K, Elgyütt A, Novotny P, Rouillé O. 2018. Expectation optimization with probabilistic guarantees in POMDPs with discounted-sum objectives. IJCAI: International Joint Conference on Artificial Intelligence vol. 2018. 4692–4699.
Chatterjee, Krishnendu, et al. Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-Sum Objectives. Vol. 2018, IJCAI, 2018, pp. 4692–99, doi:10.24963/ijcai.2018/652.

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data IST Research Explorer

Sources

arXiv 1804.10601

Search this title in

Google Scholar