Reinforcement Learning Explained via Reinforcement Learning: Towards Explainable Policies through Predictive Explanation - Intelligence Artificielle Access content directly
Conference Papers Year : 2023

Reinforcement Learning Explained via Reinforcement Learning: Towards Explainable Policies through Predictive Explanation

Abstract

In the context of reinforcement learning (RL), in order to increase trust in or understand the failings of an agent's policy, we propose predictive explanations in the form of three scenarios: best-case, worst-case and most-probable. After showing W[1]-hardness of finding such scenarios, we propose linear-time approximations. In particular, to find an approximate worst/best-case scenario, we use RL to obtain policies of the environment viewed as a hostile/favorable agent. Experiments validate the accuracy of this approach.
Fichier principal
Vignette du fichier
Reinforcement_Learning_Explained_via_Reinforcement_Learning__Towards_Explainable_Policies_through_Predictive_Explanation-1.pdf (1.23 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04011857 , version 1 (02-03-2023)

Identifiers

  • HAL Id : hal-04011857 , version 1

Cite

Léo Saulières, Martin C Cooper, Florence Dupin de Saint Cyr. Reinforcement Learning Explained via Reinforcement Learning: Towards Explainable Policies through Predictive Explanation. 15th International Conference on Agents and Artificial Intelligence (ICAART 2023), Feb 2023, Lisbon, Portugal. à paraître. ⟨hal-04011857⟩
72 View
48 Download

Share

Gmail Facebook Twitter LinkedIn More