Robust Finite-State Controllers for Uncertain POMDPs

Murat Cubuktepe, Nils Jansen, Sebastian Junges, Ahmadreza Marandi, Marnix Suilen, Ufuk Topcu

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

20 Citaten (Scopus)
125 Downloads (Pure)

Samenvatting

Uncertain partially observable Markov decision processes (uPOMDPs) allow the probabilistic transition and observation functions of standard POMDPs to belong to a so-called uncertainty set. Such uncertainty, referred to as epistemic uncertainty, captures uncountable sets of probability distributions caused by, for instance, a lack of data available. We develop an algorithm to compute finite-memory policies for uPOMDPs that robustly satisfy specifications against any admissible distribution. In general, computing such policies is theoretically and practically intractable. We provide an efficient solution to this problem in four steps. (1) We state the underlying problem as a nonconvex optimization problem with infinitely many constraints. (2) A dedicated dualization scheme yields a dual problem that is still nonconvex but has finitely many constraints. (3) We linearize this dual problem and (4) solve the resulting finite linear program to obtain locally optimal solutions to the original problem. The resulting problem formulation is exponentially smaller than those resulting from existing methods. We demonstrate the applicability of our algorithm using large instances of an aircraft collision-avoidance scenario and a novel spacecraft motion planning case study.

Originele taal-2Engels
TitelProceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)
UitgeverijAssociation for the Advancement of Artificial Intelligence (AAAI)
Pagina's11792-11800
Aantal pagina's9
ISBN van elektronische versie9781713835974
StatusGepubliceerd - 2021
Evenement35th AAAI Conference on Artificial Intelligence, AAAI 2021 - ONLINE, Virtual, Online
Duur: 2 feb. 20219 feb. 2021

Congres

Congres35th AAAI Conference on Artificial Intelligence, AAAI 2021
StadVirtual, Online
Periode2/02/219/02/21

Vingerafdruk

Duik in de onderzoeksthema's van 'Robust Finite-State Controllers for Uncertain POMDPs'. Samen vormen ze een unieke vingerafdruk.

Citeer dit