Deep Learning of Heuristics for Domain-independent Planning

Otakar Trunda, Roman Barták

Abstract

Automated planning deals with the problem of finding a sequence of actions leading from a given state to a desired state. The state-of-the-art automated planning techniques exploit informed forward search guided by a heuristic, where the heuristic (under)estimates a distance from a state to a goal state. In this paper, we present a technique to automatically construct an efficient heuristic for a given domain. The proposed approach is based on training a deep neural network using a set of solved planning problems from the domain. We use a novel way of generating features for states which doesn’t depend on usage of existing heuristics. The trained network can be used as a heuristic on any problem from the domain of interest without any limitation on the problem size. Our experiments show that the technique is competitive with popular domain-independent heuristic.

Download


Paper Citation


in Harvard Style

Trunda O. and Barták R. (2020). Deep Learning of Heuristics for Domain-independent Planning.In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-395-7, pages 79-88. DOI: 10.5220/0008950400790088


in Bibtex Style

@conference{icaart20,
author={Otakar Trunda and Roman Barták},
title={Deep Learning of Heuristics for Domain-independent Planning},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2020},
pages={79-88},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008950400790088},
isbn={978-989-758-395-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Deep Learning of Heuristics for Domain-independent Planning
SN - 978-989-758-395-7
AU - Trunda O.
AU - Barták R.
PY - 2020
SP - 79
EP - 88
DO - 10.5220/0008950400790088