Closed TheExGenesis closed 5 years ago
Full training + test set run
Main.py is not in this repo.. are you sure you are cloning the correct repo?
Sent with GitHawk
I meant train.py
How about u just modify the action space to let the agent hold only one position each time and train it?
Thanks, I'll try that. But since this is code straight from the repo, is it possible that it's a bug? Since others have trained from scratch and achieved good results, could this be a matter of versioning of the libs?
Just got it to work, after yet another clean clone. Close.
The blog post suggests the Sortino reward function avoids over-trading, but on both the original and the fixed date dataset I see wild trading rates close to 50% that invariably result in a loss of more than to 50% of the starting budget.
This is by running train.py right out of git clone. Not sure if a bug or if I'm missing something.