AI4Finance-Foundation / AI4Finance-Foundation/FinRL-Tutorials

NeurIPS2018 no speedup with increasing batch size

未关闭
#48 2 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
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

打开贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。