Skip to Main content Skip to Navigation
Conference papers

Learning from Explanations and Demonstrations: A Pilot Study

Abstract : We discuss the relationship between explainability and knowledge transfer in reinforcement learning. We argue that explainability methods, in particular methods that use counterfactuals, might help increasing sample efficiency. For this, we present a computational approach to optimize the learner's performance using explanations of another agent and discuss our results in light of effective natural language explanations for both agents and humans.
Complete list of metadata
Contributor : Mohamed Chetouani Connect in order to contact the contributor
Submitted on : Tuesday, March 9, 2021 - 11:08:36 AM
Last modification on : Wednesday, May 19, 2021 - 12:12:54 PM


  • HAL Id : hal-03152179, version 1


Silvia Tulli, Sebastian Wallkötter, Ana Paiva, Francisco Melo, Mohamed Chetouani. Learning from Explanations and Demonstrations: A Pilot Study. 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, Dec 2020, Dubin, Virtual, Ireland. pp.61-66. ⟨hal-03152179⟩



Record views