Multi-Objective Genetic Programming for Explainable Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Multi-Objective Genetic Programming for Explainable Reinforcement Learning

Abstract

Deep reinforcement learning has met noticeable successes recently for a wide range of control problems. However, this is typically based on thousands of weights and non-linearities, making solutions complex, not easily reproducible, uninterpretable and heavy. The present paper presents genetic programming approaches for building symbolic controllers. Results are competitive, in particular in the case of delayed rewards, and the solutions are lighter by orders of magnitude and much more understandable.
Fichier principal
Vignette du fichier
_EuroGP__Multi_Objective_Genetic_Programming_for_Explainable_Reinforcement_Learning.pdf (737.31 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03886307 , version 1 (06-12-2022)

Identifiers

Cite

Mathurin Videau, Alessandro Leite, Olivier Teytaud, Marc Schoenauer. Multi-Objective Genetic Programming for Explainable Reinforcement Learning. Proc. EuroGP 2022, Apr 2022, Madrid, France. pp.278-293, ⟨10.1007/978-3-031-02056-8_18⟩. ⟨hal-03886307⟩
29 View
68 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More