Zero1366166516

I previously made a CNN feature extractor for mlppolicy strategy network, which can be shared with everyone. CNN feature extractor : ``` class CustomCNN(BaseFeaturesExtractor): """ :param observation_space: (gym.Space) :param features_dim:...

I would like to ask whether this algorithm can be used in real stock trading, and how to realize the operation of the next day in the real world.

My idea is to use it in the real world to use DRL algorithm to make portfolio, such as predicting whether positions should be adjusted tomorrow and how to use...

Thank you very much for your help. Let me talk about my situation first. I am interested in quantitative investment. I am also a shareholder. I found that MLP is...

Copy that. In fact, I just want to find an example program of LSTM feature extractor.

刚才太匆忙了，我的意思是通过环境预测新的股票价格信息，然后再用算法选择换股的策略。

收到，我只是想看看怎么能用到实盘上。 另外我运行后，发现回测里，没有夏普率等，只有资金和收益率的报表，没有输出图形。 我是刚刚学python，刚刚给调试运行了，希望加下楼主微信，以便进一步学习。

已经发您邮箱了，请通过一下。

您说的明显的未来函数是什么？

我认为T日获得T+1股价其实对算法（train）来说是没有用的，因为每天只操作一次并且T+1日的操作其实T日就已经给出了，T+1日其实是给T+2日的action。 我的问题是在T+1日时，trade的算法是怎么操作的，action的产生是否与当日（T+1）的状态相关，train和trade的机制是一样的吗？ 我记得action应该是随机概率的生成，然后给定方向，根据reward调整。