Inductive synthesis of finite-state controllers for POMDPs
Roman Andriushchenko, Milan Češka, Sebastian Junges, Joost-Pieter Katoen
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.
BibTeX
@InProceedings{pmlr-v180-andriushchenko22a,
title = {Inductive synthesis of finite-state controllers for POMDPs},
author = {Andriushchenko, Roman and \v{C}e\v{s}ka, Milan and Junges, Sebastian and Katoen, Joost-Pieter},
booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence},
pages = {85--95},
year = {2022},
editor = {Cussens, James and Zhang, Kun},
volume = {180},
series = {Proceedings of Machine Learning Research},
month = {01--05 Aug},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v180/andriushchenko22a/andriushchenko22a.pdf},
url = {https://proceedings.mlr.press/v180/andriushchenko22a.html},
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.}
}