❓ How to set the LSTM step size for the actor/critic?

[fishingcatgo]

❓ How to set the LSTM step size for the actor/critic?

How to set the LSTM step size for the actor/critic?

The last 'features [:, -1,:]' or 'h-n [-1]' of feature extraction is used as a summary for a single feature. Multiple features are accumulated (cached) until the threshold step is reached before updating the actor/critic LSTM. How to set the LSTM step size for the actor/critic?
特征提取的最后一个 features[:, -1, :] 或 h_n[-1] 作为 summary单个特征，累计（缓存）多个特征，达到阈值步长再更新actor/critic LSTM.如何设置actor/critic 的LSTM步长？

Checklist

• I have checked that there is no similar issue in the repo
• I have read the documentation
• If code there is, it is minimal and working
• If code there is, it is formatted using the markdown code blocks for both code and stack traces.