Skip to Main content Skip to Navigation
New interface
Conference papers

Apprentissage adaptatif de comportements éthiques

Rémy Chaput 1 Olivier Boissier Mathieu Guillermin Salima Hassas 1 
1 SyCoSMA - Systèmes Cognitifs et Systèmes Multi-Agents
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : The increase in the use of Artificial Intelligence (AI) algorithms in applications impacting human users and actors has, as a direct consequence, the need for endowing these AI systems with ethical behaviors. While several approaches already exist, the question of adaptability to changes in contexts, users behaviors or preferences still remains open. We propose to tackle this question using Multi-Agent Reinforcement Learning of ethical behavior in different situations using Q-Tables and Dynamic Self-Organizing Maps to allow dynamic learning of the representation of the environment's state and reward functions to prescribe ethical behaviors. To evaluate this proposal, we developed a simulator of intelligent management of energy distribution in Smart Grids, evaluating different rewards functions to trigger ethical behaviors. Results show the ability to adapt to different conditions. Besides contributions on ethical adaptation, we compare our model to other learning approaches and show it performs better than a Deep Learning one (based on Actor-Critic).
Complete list of metadata
Contributor : Rémy Chaput Connect in order to contact the contributor
Submitted on : Wednesday, November 18, 2020 - 1:53:23 PM
Last modification on : Friday, October 14, 2022 - 12:49:21 PM
Long-term archiving on: : Friday, February 19, 2021 - 7:37:55 PM


Files produced by the author(s)


  • HAL Id : hal-03012127, version 1


Rémy Chaput, Olivier Boissier, Mathieu Guillermin, Salima Hassas. Apprentissage adaptatif de comportements éthiques. 28e Journées Francophones sur les Systèmes Multi-Agents (JFSMA'2020), Jun 2020, Angers, France. ⟨hal-03012127⟩



Record views


Files downloads