Predicate-based explanation of a Reinforcement Learning agent via action importance evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Predicate-based explanation of a Reinforcement Learning agent via action importance evaluation

Résumé

For the purpose of understanding the impact of a Reinforcement Learning (RL) agent's decisions on the satisfaction of a given arbitrary predicate, we present a method based on the evaluation of the importance of actions. This highlights to the user the most important action(s) (relative to the predicate) in a history of the agent's interactions with the environment. Having shown that calculating the importance of an action for a predicate to hold is #W[1]-hard, we propose a timesaving approximation. To do so, we use the most likely transitions in the environment. Experiments confirm the relevance of this approach.
Fichier principal
Vignette du fichier
HXP_paper_for_AIMLAI_Workshop___Camera_Ready.pdf (2.46 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04170188 , version 1 (25-07-2023)

Identifiants

  • HAL Id : hal-04170188 , version 1

Citer

Léo Saulières, Martin Cooper, Florence Dupin de Saint-Cyr. Predicate-based explanation of a Reinforcement Learning agent via action importance evaluation. 4th workshop on Advances in Interpretable Machine Learning and Artificial Intelligence (AIMLAI 2023) @ ECML/PKDD conference, Sep 2023, Turin, Italy. à paraître. ⟨hal-04170188⟩
126 Consultations
58 Téléchargements

Partager

Gmail Facebook X LinkedIn More