DLR-RM/stable-baselines3
Ver no GitHub[Enhancement]: Wrong gains for weight initialization
Open
#1.559 aberto em 16 de jun. de 2023
enhancementhelp wanted
Métricas do repositório
- Stars
- (6.550 stars)
- Métricas de merge de PR
- (Mesclagem média 11d 13h) (3 fundiu PRs em 30d)
Description
Enhancement
The recommended gains for the weight init depend on the used activation function, see torch docs. However, as for now the used gains are statically implemented and always the same in ActorCriticPolicies. See here.
I recommend making the gains dependent on the activation function used(, i.e. probably mainly ReLU and tanh).
If you agree with this, I would like to implement it myself and PR.
Thanks and a good day!
To Reproduce
--
Relevant log output / Error message
--
System Info
--
Checklist
- I have checked that there is no similar issue in the repo
- I have read the documentation
- I have provided a minimal working example to reproduce the bug
- I've used the markdown code blocks for both code and stack traces.