Detail publikace

Inductive Synthesis of Finite-State Controllers for POMDPs

ANDRIUSHCHENKO, R. ČEŠKA, M. JUNGES, S. KATOEN, J.

Originální název

Inductive Synthesis of Finite-State Controllers for POMDPs

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

partially observable Markov decision processes, finite-state controllers, inductive synthesis, counter-examples, abstraction 

Autoři

ANDRIUSHCHENKO, R.; ČEŠKA, M.; JUNGES, S.; KATOEN, J.

Vydáno

17. 6. 2022

Nakladatel

Proceedings of Machine Learning Research

Místo

Eindhoven

ISSN

2640-3498

Ročník

180

Číslo

180

Strany od

85

Strany do

95

Strany počet

11

BibTex

@inproceedings{BUT178215,
  author="ANDRIUSHCHENKO, R. and ČEŠKA, M. and JUNGES, S. and KATOEN, J.",
  title="Inductive Synthesis of Finite-State Controllers for POMDPs",
  booktitle="Conference on Uncertainty in Artificial Intelligence",
  year="2022",
  series="Proceedings of Machine Learning Research",
  volume="180",
  number="180",
  pages="85--95",
  publisher="Proceedings of Machine Learning Research",
  address="Eindhoven",
  issn="2640-3498"
}