algorithmic-trading

Describe your environment

N/A

Describe the enhancement

Currently it seems the max_open_trades can have significant impact on profit. The only way I have been able to find a good number is to run several back

🐛 Bug Description

Under MLP implementation there are several variables that need to be initialized. Such as loss, lr, lr_decay, lr_decay_steps, optimizer. However, it seems that the variables lr_decay andlr_decay_steps are indeed being initialized but are not being used at any point in the code.

finrl.test() return a list of int of portfolio value, it doesn't contain date data:

from finrl.test import test
account_value_sb3=test(start_date = '2021-10-18', 
                      end_date = '2021-10-19',
...
                      net_dimension = 512)
account_value_sb3

output: 
[1000000.0,
 999698.6172275314,
 999391.9308182714,
...

But portfolio analysis tool(like

According to @rspadim, functions in entropy.py could use numpy array instead of strings, as it's better to numba.

Guide on how to implement this is available in the comments in PR #311 .

Is your feature request related to a problem? Please describe.
Ugly title for asset new asset. The asset node gets New Asset title after entering the codename.

Describe the solution you'd like
auto rename by referring the codeName --> iconName
set iconName as variable.

Describe alternatives you've considered

Additional context
Add any other context or screenshots

this is how Buy & Hold Return is calculated:

        c = data.Close.values
        s.loc['Buy & Hold Return [%]'] = (c[-1] - c[0]) / c[0] * 100  # long-only return

so it's calced use day one and the day last.

Expected Behavior

Buy & Hold Return is used for compare with strategy gain. Therefore, I guess they should started at same time, since the strategy get enough data to w