DLR-RM/stable-baselines3
Voir sur GitHub[Feature Request] independently configurable learning rates for actor and critic
Open
#338 ouverte le 3 mars 2021
enhancementhelp wanted
Métriques du dépôt
- Stars
- (6 550 stars)
- Métriques de merge PR
- (Merge moyen 11j 13h) (3 PRs mergées en 30 j)
Description
🚀 Feature
independently configurable learning rates for actor and critic in AC-style algorithms
Motivation
In literature the actor is often configured to learn slower, such that the critics responses are more reliable. At least it would be nice if i could allow my hyperparameter optimizer to decide which learning rates he wants to use for actor or critic.
Pitch
Additional context
https://spinningup.openai.com/en/latest/algorithms/ddpg.html#documentation-pytorch-version