DLR-RM/stable-baselines3

[Feature Request] independently configurable learning rates for actor and critic

Open

#338 aberto em 3 de mar. de 2021

Ver no GitHub
 (11 comments) (1 reaction) (0 assignees)Python (1.407 forks)batch import
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

https://github.com/DLR-RM/stable-baselines3/blob/65100a4b040201035487363a396b84ea721eb027/stable_baselines3/ddpg/ddpg.py#L12-L26

Additional context

https://spinningup.openai.com/en/latest/algorithms/ddpg.html#documentation-pytorch-version

Guia do colaborador