Finite-memory strategies in POMDPs with long-run average objectives

Chatterjee K, Saona Urmeneta RJ, Ziliotto B. 2021. Finite-memory strategies in POMDPs with long-run average objectives. Mathematics of Operations Research., 1116.


Journal Article | Epub ahead of print | English
Abstract
Partially observable Markov decision processes (POMDPs) are standard models for dynamic systems with probabilistic and nondeterministic behaviour in uncertain environments. We prove that in POMDPs with long-run average objective, the decision maker has approximately optimal strategies with finite memory. This implies notably that approximating the long-run value is recursively enumerable, as well as a weak continuity property of the value with respect to the transition function.
Publishing Year
Date Published
2021-04-06
Journal Title
Mathematics of Operations Research
Article Number
1116
IST-REx-ID

Cite this

Chatterjee K, Saona Urmeneta RJ, Ziliotto B. Finite-memory strategies in POMDPs with long-run average objectives. Mathematics of Operations Research. 2021. doi:10.1287/moor.2020.1116
Chatterjee, K., Saona Urmeneta, R. J., & Ziliotto, B. (2021). Finite-memory strategies in POMDPs with long-run average objectives. Mathematics of Operations Research. Institute for Operations Research and the Management Sciences. https://doi.org/10.1287/moor.2020.1116
Chatterjee, Krishnendu, Raimundo J Saona Urmeneta, and Bruno Ziliotto. “Finite-Memory Strategies in POMDPs with Long-Run Average Objectives.” Mathematics of Operations Research. Institute for Operations Research and the Management Sciences, 2021. https://doi.org/10.1287/moor.2020.1116.
K. Chatterjee, R. J. Saona Urmeneta, and B. Ziliotto, “Finite-memory strategies in POMDPs with long-run average objectives,” Mathematics of Operations Research. Institute for Operations Research and the Management Sciences, 2021.
Chatterjee K, Saona Urmeneta RJ, Ziliotto B. 2021. Finite-memory strategies in POMDPs with long-run average objectives. Mathematics of Operations Research., 1116.
Chatterjee, Krishnendu, et al. “Finite-Memory Strategies in POMDPs with Long-Run Average Objectives.” Mathematics of Operations Research, 1116, Institute for Operations Research and the Management Sciences, 2021, doi:10.1287/moor.2020.1116.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

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

Export

Marked Publications

Open Data IST Research Explorer

Sources

arXiv 1904.13360

Search this title in

Google Scholar