AI4Finance-Foundation / AI4Finance-Foundation/FinRL-Tutorials
NeurIPS2018 no speedup with increasing batch size
未關閉
question
- 主要語言
- Jupyter Notebook
- 星號
- 1.2k
- 分支
- 435
- PR 合併指標
- 30 天內沒有已合併 PR
描述
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?
貢獻指南
評估
這個 Issue 還沒有評估資料。