Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Barde, Paul"'
Training multiple agents to coordinate is an essential problem with applications in robotics, game theory, economics, and social sciences. However, most existing Multi-Agent Reinforcement Learning (MARL) methods are online and thus impractical for re
Externí odkaz:
http://arxiv.org/abs/2305.17198
Autor:
Barde, Paul, Karch, Tristan, Nowrouzezahrai, Derek, Moulin-Frier, Clément, Pal, Christopher, Oudeyer, Pierre-Yves
We are interested in interactive agents that learn to coordinate, namely, a $builder$ -- which performs actions but ignores the goal of the task, i.e. has no access to rewards -- and an $architect$ which guides the builder towards the goal of the tas
Externí odkaz:
http://arxiv.org/abs/2112.07342
Autor:
Jeon, Wonseok, Su, Chen-Yang, Barde, Paul, Doan, Thang, Nowrouzezahrai, Derek, Pineau, Joelle
Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularized IRL applies strongly convex regularizers to the learner's policy in
Externí odkaz:
http://arxiv.org/abs/2010.03691
Autor:
Barde, Paul, Roy, Julien, Jeon, Wonseok, Pineau, Joelle, Pal, Christopher, Nowrouzezahrai, Derek
Publikováno v:
Advances in Neural Information Processing Systems 33 (2020)
Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones -- and a generator's policy to produce trajectories that can fool this discriminator. This alternated optimiza
Externí odkaz:
http://arxiv.org/abs/2006.13258
Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems where we seek to recover both policies for our agents and reward functions that promote expert-like behavior.
Externí odkaz:
http://arxiv.org/abs/2002.10525
In multi-agent reinforcement learning, discovering successful collective behaviors is challenging as it requires exploring a joint action space that grows exponentially with the number of agents. While the tractability of independent agent-wise explo
Externí odkaz:
http://arxiv.org/abs/1908.02269
Autor:
Barde, Paul, Karch, Tristan, Nowrouzezahrai, Derek, Moulin-Frier, Clément, Pal, Christopher, Oudeyer, Pierre-Yves
Publikováno v:
International Conference on Learning Representations
International Conference on Learning Representations, Apr 2022, Virtual, France
International Conference on Learning Representations, Apr 2022, Virtual, France
We are interested in interactive agents that learn to coordinate, namely, a $builder$ -- which performs actions but ignores the goal of the task, i.e. has no access to rewards -- and an $architect$ which guides the builder towards the goal of the tas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1017c17a0a76a4187faaf4cedad6420
https://hal.science/hal-03901793
https://hal.science/hal-03901793