Result Details
Inductive Synthesis of Finite-State Controllers for POMDPs
Češka Milan, doc. RNDr., Ph.D., DITS (FIT)
JUNGES, S.
KATOEN, J.
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.
partially observable Markov decision processes, finite-state controllers, inductive synthesis, counter-examples, abstraction
@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",
journal="Proceedings of Machine Learning Research",
volume="180",
number="180",
pages="85--95",
publisher="Proceedings of Machine Learning Research",
address="Eindhoven"
}