« Apprentissage par renforcement avec borne de confiance supérieure » : différence entre les versions
Aucun résumé des modifications |
Aucun résumé des modifications |
||
| Ligne 14 : | Ligne 14 : | ||
== Anglais == | == Anglais == | ||
'''Reinforcement Learning with the Upper Confidence Bound''' | '''Reinforcement Learning with the Upper Confidence Bound''' | ||
Recall the general setup for reinforcement learning: we have well-defined actions that we can take, so we let the machine figure out how to maximize its reward based on the consequences of those actions. | Recall the general setup for reinforcement learning: we have well-defined actions that we can take, so we let the machine figure out how to maximize its reward based on the consequences of those actions. | ||
Version du 9 mars 2019 à 11:31
Domaine
Vocabulary
Définition
texte ici
Français
terme_français
Anglais
Reinforcement Learning with the Upper Confidence Bound
Recall the general setup for reinforcement learning: we have well-defined actions that we can take, so we let the machine figure out how to maximize its reward based on the consequences of those actions.
The Upper Confidence Bound algorithm is a formalization of this idea, where the machine attempts to determine a single action it can take that will maximize its expected return.
Contributeurs: Evan Brach, Claude Coulombe, Gérard Pelletier, Jacques Barolet, wiki
