In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in artificial intelligence, focusing on the notion of *action* and *interactivity*. In reinforcement learning, an agent receives information from its environment and acts. The goal is to maximize a constraint called “the reward”. Planning (Anticipating long-term consequences and higher rewards) and Exploration (How to gather as much information as possible in a minimal time) are central to this topic.The term “Reinforcement Learning” comes from psychology, and ever since, Artificial In- telligence and Cognitive Science have borrowed from each other. Cognitive study inspired early AI pioneers, and computers’ modularity influenced cognitivism. Then,...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
The thesis contributions resolves around sequential decision taking and more precisely Reinforcement...
The thesis contributions resolves around sequential decision taking and more precisely Reinforcement...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
Dans cette thèse de doctorat, nous étudions l'apprentissage séquentiel (dit ``par renforcement'') en...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
The thesis contributions resolves around sequential decision taking and more precisely Reinforcement...
The thesis contributions resolves around sequential decision taking and more precisely Reinforcement...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
In this Ph.D. thesis, we study sequential decision making (a.k.a Reinforcement Learning or RL) in ar...
Dans cette thèse de doctorat, nous étudions l'apprentissage séquentiel (dit ``par renforcement'') en...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
International audienceIn contrast with research work in Artificial Intelligence, which can test desi...
The thesis contributions resolves around sequential decision taking and more precisely Reinforcement...
The thesis contributions resolves around sequential decision taking and more precisely Reinforcement...