Zobrazeno 1 - 10
of 443
pro vyhledávání: '"Gilbert Nicolas"'
Autor:
Perrin-Gilbert, Nicolas
This paper presents AFU, an off-policy deep RL algorithm addressing in a new way the challenging "max-Q problem" in Q-learning for continuous action spaces, with a solution based on regression and conditional gradient scaling. AFU has an actor but it
Externí odkaz:
http://arxiv.org/abs/2404.16159
Autor:
Kim, Jason Z., Perrin-Gilbert, Nicolas, Narmanli, Erkan, Klein, Paul, Myers, Christopher R., Cohen, Itai, Waterfall, Joshua J., Sethna, James P.
Natural systems with emergent behaviors often organize along low-dimensional subsets of high-dimensional spaces. For example, despite the tens of thousands of genes in the human genome, the principled study of genomics is fruitful because biological
Externí odkaz:
http://arxiv.org/abs/2403.01078
Demonstrations are commonly used to speed up the learning process of Deep Reinforcement Learning algorithms. To cope with the difficulty of accessing multiple demonstrations, some algorithms have been developed to learn from a single demonstration. I
Externí odkaz:
http://arxiv.org/abs/2402.09355
Autor:
Sigaud, Olivier, Baldassarre, Gianluca, Colas, Cedric, Doncieux, Stephane, Duro, Richard, Oudeyer, Pierre-Yves, Perrin-Gilbert, Nicolas, Santucci, Vieri Giuliano
A lot of recent machine learning research papers have ``open-ended learning'' in their title. But very few of them attempt to define what they mean when using the term. Even worse, when looking more closely there seems to be no consensus on what dist
Externí odkaz:
http://arxiv.org/abs/2311.00344
In this paper we present a layered approach for multi-agent control problem, decomposed into three stages, each building upon the results of the previous one. First, a high-level plan for a coarse abstraction of the system is computed, relying on par
Externí odkaz:
http://arxiv.org/abs/2307.06758
Autor:
Macé, Valentin, Boige, Raphaël, Chalumeau, Felix, Pierrot, Thomas, Richard, Guillaume, Perrin-Gilbert, Nicolas
In the context of neuroevolution, Quality-Diversity algorithms have proven effective in generating repertoires of diverse and efficient policies by relying on the definition of a behavior space. A natural goal induced by the creation of such a repert
Externí odkaz:
http://arxiv.org/abs/2303.16207
Autor:
Chalumeau, Felix, Pierrot, Thomas, Macé, Valentin, Flajolet, Arthur, Beguir, Karim, Cully, Antoine, Perrin-Gilbert, Nicolas
A fascinating aspect of nature lies in its ability to produce a collection of organisms that are all high-performing in their niche. Quality-Diversity (QD) methods are evolutionary algorithms inspired by this observation, that obtained great results
Externí odkaz:
http://arxiv.org/abs/2211.13742
Deep Reinforcement Learning has been successfully applied to learn robotic control. However, the corresponding algorithms struggle when applied to problems where the agent is only rewarded after achieving a complex task. In this context, using demons
Externí odkaz:
http://arxiv.org/abs/2211.04786
When cast into the Deep Reinforcement Learning framework, many robotics tasks require solving a long horizon and sparse reward problem, where learning algorithms struggle. In such context, Imitation Learning (IL) can be a powerful approach to bootstr
Externí odkaz:
http://arxiv.org/abs/2204.07404
Publikováno v:
Retrovirology, Vol 6, Iss Suppl 2, p P32 (2009)
Externí odkaz:
https://doaj.org/article/da8f309b48424c12bee6684e514de959
