D 2018

Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-Sum Objectives

CHATTERJEE, Krishnendu; Adrián ELGYUTT; Petr NOVOTNÝ and Owen ROUILLÉ

Basic information

Original name

Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-Sum Objectives

Authors

CHATTERJEE, Krishnendu; Adrián ELGYUTT; Petr NOVOTNÝ and Owen ROUILLÉ

Edition

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI 2018), p. 4692--4699, 7 pp. 2018

Publisher

ijcai.org

Other information

Type of outcome

Proceedings paper

Confidentiality degree

is not subject to a state or trade secret

Publication form

electronic version available online

ISBN

978-0-9992411-2-7

EID Scopus

2-s2.0-85055700702

Keywords in English

POMDPs; Planning under Uncertainty; Planning with Incomplete Information

Tags

International impact, Reviewed
Changed: 26/9/2019 10:15, doc. RNDr. Petr Novotný, Ph.D.

Abstract

In the original language

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 to obtain risk-averse policies, but ignore 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.