DLR-RM/stable-baselines3
Ver no GitHub[Feature Request] independently configurable learning rates for actor and critic
Open
#338 aberto em 3 de mar. de 2021
enhancementhelp wanted
Métricas do repositório
- Stars
- (6.550 stars)
- Métricas de merge de PR
- (Mesclagem média 11d 13h) (3 fundiu PRs em 30d)
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