Apprentissage par renforcement profondL'apprentissage par renforcement profond (en anglais : deep reinforcement learning ou deep RL) est un sous-domaine de l'apprentissage automatique (en anglais : machine learning) qui combine l'apprentissage par renforcement et l'apprentissage profond (en anglais : deep learning). L'apprentissage par renforcement considère le problème d'un agent informatique (par exemple, un robot, un agent conversationnel, un personnage dans un jeu vidéo, etc.) qui apprend à prendre des décisions par essais et erreurs.
Synapsethumb|400px|Synapse entre deux neurones. La synapse (du grec , « contact, point de jonction », dérivé de , « joindre, connecter ») est une zone de contact fonctionnelle qui s'établit entre deux neurones, ou entre un neurone et une autre cellule (cellules musculaires, récepteurs sensoriels...). Elle assure la conversion d'un potentiel d'action déclenché dans le neurone présynaptique en un signal dans la cellule postsynaptique. On estime, pour certains types cellulaires (par exemple cellule pyramidale, cellule de Purkinje.
Natural exponential familyIn probability and statistics, a natural exponential family (NEF) is a class of probability distributions that is a special case of an exponential family (EF). The natural exponential families (NEF) are a subset of the exponential families. A NEF is an exponential family in which the natural parameter η and the natural statistic T(x) are both the identity. A distribution in an exponential family with parameter θ can be written with probability density function (PDF) where and are known functions.
Reinforcement learning from human feedbackIn machine learning, reinforcement learning from human feedback (RLHF) or reinforcement learning from human preferences is a technique that trains a "reward model" directly from human feedback and uses the model as a reward function to optimize an agent's policy using reinforcement learning (RL) through an optimization algorithm like Proximal Policy Optimization. The reward model is trained in advance to the policy being optimized to predict if a given output is good (high reward) or bad (low reward).
Multi-agent reinforcement learningMulti-agent reinforcement learning (MARL) is a sub-field of reinforcement learning. It focuses on studying the behavior of multiple learning agents that coexist in a shared environment. Each agent is motivated by its own rewards, and does actions to advance its own interests; in some environments these interests are opposed to the interests of other agents, resulting in complex group dynamics. Multi-agent reinforcement learning is closely related to game theory and especially repeated games, as well as multi-agent systems.
Exponential dispersion modelIn probability and statistics, the class of exponential dispersion models (EDM) is a set of probability distributions that represents a generalisation of the natural exponential family. Exponential dispersion models play an important role in statistical theory, in particular in generalized linear models because they have a special structure which enables deductions to be made about appropriate statistical inference. There are two versions to formulate an exponential dispersion model.
Self-playSelf-play is a technique for improving the performance of reinforcement learning agents. Intuitively, agents learn to improve their performance by playing "against themselves". In multi-agent reinforcement learning experiments, researchers try to optimize the performance of a learning agent on a given task, in cooperation or competition with one or more agents. These agents learn by trial-and-error, and researchers may choose to have the learning algorithm play the role of two or more of the different agents.
