TERMIUM Plus^®

Fiche 1,  Justifications,  Anglais

Record number: 1, Textual support number: 1 CONT

Reinforcement learning describes a large class of learning problems characteristic of autonomous agents interacting in an environment: sequential decision-making problems with delayed reward. Reinforcement learning algorithms seek to learn a policy (mapping from states to actions) that maximize the reward received over time.  2, fiche 1, Anglais, - reinforcement%20learning%20algorithm

Fiche 1,  Justifications,  Français

Fiche 1,  Justifications,  Espagnol