Search and Explore: Symbiotic Policy Synthesis in POMDPs

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149417" target="_blank" >RIV/00216305:26230/23:PU149417 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-031-37709-9_6" target="_blank" >http://dx.doi.org/10.1007/978-3-031-37709-9_6</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-37709-9_6" target="_blank" >10.1007/978-3-031-37709-9_6</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Search and Explore: Symbiotic Policy Synthesis in POMDPs

Popis výsledku v původním jazyce

This paper marries two state-of-the-art controller synthesis methods for partially observable Markov decision processes (POMDPs), a prominent model in sequential decision making under uncertainty. A central issue is to find a POMDP controller - that solely decides based on the observations seen so far - to achieve a total expected reward objective. As finding optimal controllers is undecidable, we concentrate on synthesising good finite-state controllers (FSCs). We do so by tightly integrating two modern, orthogonal methods for POMDP controller synthesis: a belief-based and an inductive approach. The former method obtains an FSC from a finite fragment of the so-called belief MDP, an MDP that keeps track of the probabilities of equally observable POMDP states. The latter is an inductive search technique over a set of FSCs, e.g., controllers with a fixed memory size. The key result of this paper is a symbiotic anytime algorithm that tightly integrates both approaches such that each profits from the controllers constructed by the other. Experimental results indicate a substantial improvement in the value of the controllers while significantly reducing the synthesis time and memory footprint.

Název v anglickém jazyce

Search and Explore: Symbiotic Policy Synthesis in POMDPs

Popis výsledku anglicky

This paper marries two state-of-the-art controller synthesis methods for partially observable Markov decision processes (POMDPs), a prominent model in sequential decision making under uncertainty. A central issue is to find a POMDP controller - that solely decides based on the observations seen so far - to achieve a total expected reward objective. As finding optimal controllers is undecidable, we concentrate on synthesising good finite-state controllers (FSCs). We do so by tightly integrating two modern, orthogonal methods for POMDP controller synthesis: a belief-based and an inductive approach. The former method obtains an FSC from a finite fragment of the so-called belief MDP, an MDP that keeps track of the probabilities of equally observable POMDP states. The latter is an inductive search technique over a set of FSCs, e.g., controllers with a fixed memory size. The key result of this paper is a symbiotic anytime algorithm that tightly integrates both approaches such that each profits from the controllers constructed by the other. Experimental results indicate a substantial improvement in the value of the controllers while significantly reducing the synthesis time and memory footprint.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA23-06963S" target="_blank" >GA23-06963S: VESCAA: Verifikovatelná a efektivní syntéza kontrolerů pro autonomní agenty</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Aided Verification

ISBN

978-3-031-37708-2

ISSN

—

e-ISSN

—

Počet stran výsledku

23

Strana od-do

113-135

Název nakladatele

Springer Verlag

Místo vydání

Cham

Místo konání akce

Paříž

Datum konání akce

17. 7. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—