Finite-Memory Strategies in POMDPs with Long-Run Average Objectives
Work
Year: 2021
Type: article
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 wit... more
Institutions Institute of Science and Technology Austria, Centre de Recherche en Mathématiques de la Décision, Université Paris Sciences et Lettres, Université Paris Dauphine-PSL
Cites: 33
Cited by: 4
Related to: 10
FWCI: 0.443
Citation percentile (by year/subfield): 57.43
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Sustainable Development Goal Peace, justice, and strong institutions
Open Access status: green