Dixing (Dex) Xu

I think shorting is more about actions. Can you explain a bit more on why do you think changing the input data would help the agent's decision?

Yes, what David wrote is a good method. Besides, you can change the activation function to allow negative output. On Fri, Jul 6, 2018, 1:52 PM David Blom wrote: >...

Oh, I forgot to mention you can use the same variable to control long/short position. I don't quite understand why there needs to be two separate variables for long/short, if...

> Do you still need to change the loss function? I don't think so, right? I think you still need to change the loss function. Besides tanh, you can try...

there is one [data.db at release](https://github.com/ZhengyaoJiang/PGPortfolio/releases)

`nntrader` is the name we used before publishing the repo. Although I only see `.idea` error, I think you can just delete `.idea` folder if that's the problem.

I think you can find the 'expression' w (how w is generated) at `network.py`, something looks like https://github.com/ZhengyaoJiang/PGPortfolio/blob/a2daa72d5ed62acad0a947f0bc79970c6356514b/pgportfolio/learn/network.py#L102-L123

Hi! What is the backtest result?

> do you have some clues/ideas why this might happen? There are many reasons this might happen. Like configuration of hyperparameters, technical bugs, etc. I am not sure what's the...

> So you doesn't experienced such equally-distributed model in any of your experiments? Not really, the PVM initialization is uniform, so it seems to me the uniform behavior is like...