Predictive Explanations for and by Reinforcement Learning - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Predictive Explanations for and by Reinforcement Learning

Résumé

In order to understand a reinforcement learning (RL) agent's behavior within its environment, we propose an answer to `What is likely to happen?' in the form of a predictive explanation. It is composed of three scenarios: best-case, worst-case and most-probable which we show are computationally difficult to find (W[1]-hard). We propose linear-time approximations by considering the environment as a favorable/hostile/neutral RL agent. Experiments validate this approach. Furthermore, we give a dynamic-programming algorithm to find an optimal summary of a long scenario.
Fichier principal
Vignette du fichier
SXp_paper___Extended_version___final_version.pdf (2.49 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04654797 , version 1 (23-07-2024)

Identifiants

Citer

Léo Saulières, Martin C Cooper, Florence Dupin de Saint-Cyr. Predictive Explanations for and by Reinforcement Learning. 15th international conference on Agents and Artificial Intelligence (ICAART 2023), Feb 2023, Lisbon, Portugal. pp.115-140, ⟨10.1007/978-3-031-55326-4_6⟩. ⟨hal-04654797⟩
10 Consultations
17 Téléchargements

Altmetric

Partager

More