---
res:
  bibo_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.
    @eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Krishnendu
      foaf_name: Chatterjee, Krishnendu
      foaf_surname: Chatterjee
      foaf_workInfoHomepage: http://www.librecat.org/personId=2E5DCA20-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0002-4561-241X
  - foaf_Person:
      foaf_givenName: Raimundo J
      foaf_name: Saona Urmeneta, Raimundo J
      foaf_surname: Saona Urmeneta
      foaf_workInfoHomepage: http://www.librecat.org/personId=BD1DF4C4-D767-11E9-B658-BC13E6697425
    orcid: 0000-0001-5103-038X
  - foaf_Person:
      foaf_givenName: Bruno
      foaf_name: Ziliotto, Bruno
      foaf_surname: Ziliotto
  bibo_doi: 10.1287/moor.2020.1116
  bibo_issue: '1'
  bibo_volume: 47
  dct_date: 2022^xs_gYear
  dct_identifier:
  - UT:000731918100001
  dct_isPartOf:
  - http://id.crossref.org/issn/0364-765X
  - http://id.crossref.org/issn/1526-5471
  dct_language: eng
  dct_publisher: Institute for Operations Research and the Management Sciences@
  dct_subject:
  - Management Science and Operations Research
  - General Mathematics
  - Computer Science Applications
  dct_title: Finite-memory strategies in POMDPs with long-run average objectives@
...