Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Barlier, Merwan"'
Publikováno v:
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems
This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before introducing a novel algorithm based on a noisy policy-switching proced
Externí odkaz:
http://arxiv.org/abs/2402.13930
Autor:
Daoudi, Paul, Mavkov, Bojan, Robu, Bogdan, Prieur, Christophe, Witrant, Emmanuel, Barlier, Merwan, Santos, Ludovic Dos
Publikováno v:
2024 IEEE Conference on Control Technology and Applications (CCTA)
This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully tuned Prop
Externí odkaz:
http://arxiv.org/abs/2402.13654
We address private deep offline reinforcement learning (RL), where the goal is to train a policy on standard control tasks that is differentially private (DP) with respect to individual trajectories in the dataset. To achieve this, we introduce PriMO
Externí odkaz:
http://arxiv.org/abs/2402.05525
Publikováno v:
Proceedings of the the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024)
Off-dynamics Reinforcement Learning (ODRL) seeks to transfer a policy from a source environment to a target environment characterized by distinct yet similar dynamics. In this context, traditional RL agents depend excessively on the dynamics of the s
Externí odkaz:
http://arxiv.org/abs/2312.15474
We introduce the safe best-arm identification framework with linear feedback, where the agent is subject to some stage-wise safety constraint that linearly depends on an unknown parameter vector. The agent must take actions in a conservative way so a
Externí odkaz:
http://arxiv.org/abs/2309.08709
We address in this paper a particular instance of the multi-agent linear stochastic bandit problem, called clustered multi-agent linear bandits. In this setting, we propose a novel algorithm leveraging an efficient collaboration between the agents in
Externí odkaz:
http://arxiv.org/abs/2309.08710
Autor:
Barlier, Merwan
Cette thèse s'inscrit dans le cadre de l'apprentissage par renforcement pour les systèmes de dialogue. Ce document propose différentes manières de considérer l'être humain, interlocuteur du système de dialogue. Après un aperçu des limites du
Externí odkaz:
http://www.theses.fr/2018LIL1I087/document
Publikováno v:
AAMAS 2018-the 17th International Conference on Autonomous Agents and Multiagent Systems
AAMAS 2018-the 17th International Conference on Autonomous Agents and Multiagent Systems, Jul 2018, Stockholm, Sweden. pp.9
AAMAS 2018-the 17th International Conference on Autonomous Agents and Multiagent Systems, Jul 2018, Stockholm, Sweden. pp.9
International audience; One major drawback of Reinforcement Learning (RL) Spoken Dialogue Systems is that they inherit from the general explorationrequirements of RL which makes them hard to deploy from an industry perspective. On the other hand, ind
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e193575443b1f89f6a5d2fdbfb2160e6
https://hal.archives-ouvertes.fr/hal-01945831/document
https://hal.archives-ouvertes.fr/hal-01945831/document
Autor:
Laroche, Romain, Barlier, Merwan
Publikováno v:
AAAI-17-Thirty-First AAAI Conference on Artificial Intelligence
AAAI-17-Thirty-First AAAI Conference on Artificial Intelligence, Feb 2017, San Francisco, United States. pp.7
AAAI-17-Thirty-First AAAI Conference on Artificial Intelligence, Feb 2017, San Francisco, United States. pp.7
This article addresses a particular Transfer Reinforcement Learning (RL) problem: when dynamics do not change from one task to another, and only the reward function does. Our method relies on two ideas, the first one is that transition samples obtain
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4437b8622419d3ce6bc8240bcd9b525a
https://hal.archives-ouvertes.fr/hal-01548649
https://hal.archives-ouvertes.fr/hal-01548649