Publication detail

Inductive Synthesis of Finite-State Controllers for POMDPs

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

Original Title

Inductive Synthesis of Finite-State Controllers for POMDPs

Type

conference paper

Language

English

Original Abstract

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.

Keywords

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

Authors

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

Released

17. 6. 2022

Publisher

Proceedings of Machine Learning Research

Location

Eindhoven

ISBN

2640-3498

Year of study

180

Number

180

Pages from

85

Pages to

95

Pages count

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"
}