edoc

Reinforcement Learning for Planning Heuristics

Ferber, Patrick and Helmert, Malte and Hoffmann, Jörg. (2020) Reinforcement Learning for Planning Heuristics. Proceedings of the 1st Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL). pp. 119-126.

[img] PDF - Published Version
611Kb

Official URL: https://edoc.unibas.ch/81224/

Downloads: Statistics Overview

Abstract

Informed heuristics are essential for the success of heuristic search algorithms. But, it is difficult to develop a new heuris- tic which is informed on various tasks. Instead, we propose a framework that trains a neural network as heuristic for the tasks it is supposed to solve. We present two reinforcement learning approaches to learn heuristics for fixed state spaces and fixed goals. Our first approach uses approximate value iteration, our second ap- proach uses searches to generate training data. We show that in some domains our approaches outperform previous work, and we point out potentials for future improvements.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Artificial Intelligence (Helmert)
UniBasel Contributors:Ferber, Patrick and Helmert, Malte
Item Type:Other
Note:Publication type according to Uni Basel Research Database: Other publications
Language:English
Related URLs:
edoc DOI:
Last Modified:23 Feb 2021 12:28
Deposited On:23 Feb 2021 12:28

Repository Staff Only: item control page