AI4Finance-Foundation / AI4Finance-Foundation/FinRL-Tutorials
NeurIPS2018 no speedup with increasing batch size
未关闭
question
- 主要语言
- Jupyter Notebook
- 星标
- 1.2k
- 派生
- 435
- PR 合并指标
- 30 天内没有已合并 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?
贡献指南
评估
这个 Issue 还没有评估数据。