DLR-RM/stable-baselines3
Vedi su GitHub[Feature Request] independently configurable learning rates for actor and critic
Open
#338 aperta il 3 mar 2021
enhancementhelp wanted
Metriche repository
- Star
- (6550 star)
- Metriche merge PR
- (Merge medio 11g 13h) (3 PR mergiate in 30 g)
Descrizione
🚀 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