AI4Finance-Foundation / AI4Finance-Foundation/FinRL-Tutorials
NeurIPS2018 no speedup with increasing batch size
Ouverte
question
- Langage dominant
- Jupyter Notebook
- Étoiles
- 1.2k
- Forks
- 435
- Métriques de merge des PR
- Aucune PR mergée en 30 j
Description
I tested demo NeurIPS2018 with stablebaseline3, I used SAC agent, and I trained with GPU. While I increase batch size from 128 to 512, I found no changing for GPU memories and utilization rate.
The version I used as below:
stable-baselines3==1.5.0
torch==1.10.0
Training time has no change with chaning batch size, what would be the problem?
Guide de contribution
Ouvrir le guide de contribution
Évaluation
Cette issue n'a pas encore été évaluée.