Backward explanations via redefinition of predicates - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Backward explanations via redefinition of predicates

Résumé

History eXplanation based on Predicates (HXP), studies the behavior of a Reinforcement Learning (RL) agent in a sequence of agent's interactions with the environment (a history), through the prism of an arbitrary predicate. To this end, an action importance score is computed for each action in the history. The explanation consists in displaying the most important actions to the user. As the calculation of an action's importance is #W[1]-hard, it is necessary for long histories to approximate the scores, at the expense of their quality. We therefore propose a new HXP method, called Backward-HXP, to provide explanations for these histories without having to approximate scores. Experiments show the ability of B-HXP to summarise long histories.
Fichier principal
Vignette du fichier
HXP____backward_HXP___ECAI(1).pdf (441.25 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04669413 , version 1 (08-08-2024)
hal-04669413 , version 2 (08-08-2024)

Identifiants

  • HAL Id : hal-04669413 , version 1

Citer

Léo Saulières, Martin Cooper, Florence Dupin de Saint-Cyr. Backward explanations via redefinition of predicates. 27th European Conference on Artifical Intelligence (ECAI-2024), Oct 2024, Saint Jacques De Compostelle, Spain. ⟨hal-04669413v1⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More