Inductive Synthesis of Finite-State Controllers for POMDPs
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU144764" target="_blank" >RIV/00216305:26230/22:PU144764 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Inductive Synthesis of Finite-State Controllers for POMDPs
Original language description
We present a novel learning framework to obtain finite-state controllers (FSCs) for partially observable Markov decision processes and illustrate its applicability for indefinite-horizon specifications. Our framework builds on oracle-guided inductive synthesis to explore a design space compactly representing available FSCs. The inductive synthesis approach consists of two stages: The outer stage determines the design space, i.e., the set of FSC candidates, while the inner stage efficiently explores the design space. This framework is easily generalisable and shows promising results when compared to existing approaches. Experiments indicate that our technique is (i) competitive to state-of-the-art belief-based approaches for indefinite-horizon properties, (ii) yields smaller FSCs than existing methods for several POMDP models, and (iii) naturally treats multi-objective specifications.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GJ20-02328Y" target="_blank" >GJ20-02328Y: CAQtuS: Computer-Aided Quantitative Synthesis</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Conference on Uncertainty in Artificial Intelligence
ISBN
—
ISSN
2640-3498
e-ISSN
—
Number of pages
11
Pages from-to
85-95
Publisher name
Proceedings of Machine Learning Research
Place of publication
Eindhoven
Event location
Eindhoven
Event date
Aug 1, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—