International audienceInitially developed in the field of artificial intelligence, reinforcement learning methods are an essential component of adaptive robotic control architectures. Two main classes of algorithms have been proposed: with and without internal models of the world. The first one has heavy computational costs but is very adaptive, while the second one is cheap but slow to converge. The combination of these algorithms within a single robotic architecture could possibly benefit from the advantages of each one. We present here these two families of algorithms, as well as the combination methods that have been proposed and tested in the neuroscience and robotics field.Développées initialement dans le cadre de l’intelligence arti...
L’objectif principal de cette thèse est de proposer une nouvelle méthode d’adaptation en ligne de l’...
This PhD thesis has been interested in two fields of artificial intelligence : reinforcement learnin...
L'idée maîtresse de notre travail de thèse définie l'apprentissage conditionné comme la "brique" élé...
The aim of this work is to build fault tolerant cooperative multi-robots systems. Our approach uses ...
Reinforcement learning has been widely applied to solve a diverse set of learning tasks, from board ...
In this work, we study how the notion of behavioral habit, inspired from the study of biology, can b...
The multi-robot systems coordination is a complex task requiring the execution of computationaly int...
Dans cette thèse, nous proposons d'intégrer la notion d'habitude comportementale au sein d'une archi...
The field of reinforcement learning, developed during the nineteen-eighties and nineties, is a branc...
For several years now, mobile robotic is trying to escape from the amniotic space of research labora...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
La coordination d'un système multi-robots est une tâche complexe nécessitant l'exécution d'algorithm...
Quand les robots doivent affronter le monde réel, ils doivent s'adapter à diverses situations imprév...
L’objectif principal de cette thèse est de proposer une nouvelle méthode d’adaptation en ligne de l’...
This PhD thesis has been interested in two fields of artificial intelligence : reinforcement learnin...
L'idée maîtresse de notre travail de thèse définie l'apprentissage conditionné comme la "brique" élé...
The aim of this work is to build fault tolerant cooperative multi-robots systems. Our approach uses ...
Reinforcement learning has been widely applied to solve a diverse set of learning tasks, from board ...
In this work, we study how the notion of behavioral habit, inspired from the study of biology, can b...
The multi-robot systems coordination is a complex task requiring the execution of computationaly int...
Dans cette thèse, nous proposons d'intégrer la notion d'habitude comportementale au sein d'une archi...
The field of reinforcement learning, developed during the nineteen-eighties and nineties, is a branc...
For several years now, mobile robotic is trying to escape from the amniotic space of research labora...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
La coordination d'un système multi-robots est une tâche complexe nécessitant l'exécution d'algorithm...
Quand les robots doivent affronter le monde réel, ils doivent s'adapter à diverses situations imprév...
L’objectif principal de cette thèse est de proposer une nouvelle méthode d’adaptation en ligne de l’...
This PhD thesis has been interested in two fields of artificial intelligence : reinforcement learnin...
L'idée maîtresse de notre travail de thèse définie l'apprentissage conditionné comme la "brique" élé...