Aller au contenu
Atlas de l'IA

Apprentissage par renforcement

Apprendre des séquences de décisions par essai, erreur et récompense différée

OVERVIEW

Tous les concepts
6
Débutant
2
Intermédiaire
3
Expert
1

Reinforcement learning addresses problems that have no answer key, only consequences: whether a step was good may only be revealed much later as reward. It introduces the vocabulary of agent, environment, state, action and reward, and approaches optimal behaviour through two families of ideas — value functions and policy gradients.