Enhancing Reinforcement Learning Agents with Local Guides - Pôle Automatique et Diagnostic Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Enhancing Reinforcement Learning Agents with Local Guides

Paul Daoudi
  • Fonction : Auteur
  • PersonId : 1243056
Ludovic Dos Santos
Merwan Barlier
  • Fonction : Auteur
  • PersonId : 1243058

Résumé

This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before introducing a novel algorithm based on a noisy policy-switching procedure. This approach builds on a proper Approximate Policy Evaluation (APE) scheme to provide a perturbation that carefully leads the local guides towards better actions. We evaluated our method on a set of classical Reinforcement Learning problems, including safetycritical systems where the agent cannot enter some areas at the risk of triggering catastrophic consequences. In all the proposed environments, our agent proved to be efficient at leveraging those policies to improve the performance of any APE-based Reinforcement Learning algorithm, especially in its first learning stages.
Fichier principal
Vignette du fichier
Final_Reinforcement_Learning_with_Local_Guides.pdf (4.3 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04052358 , version 1 (31-03-2023)
hal-04052358 , version 2 (24-12-2023)

Identifiants

  • HAL Id : hal-04052358 , version 1

Citer

Paul Daoudi, Bogdan Robu, Christophe Prieur, Ludovic Dos Santos, Merwan Barlier. Enhancing Reinforcement Learning Agents with Local Guides. AAMAS 2023 - 22nd International Conference on Autonomous Agents and Multiagent Systems, May 2023, Londres, United Kingdom. pp.829-838. ⟨hal-04052358v1⟩
183 Consultations
187 Téléchargements

Partager

Gmail Facebook X LinkedIn More