FinRL-Trading issues

adjusting prices with 'ajexdi'

Great work just have a couple of questions I'm looking at preprocess code and see that you used the field 'ajexdi' from the raw file 'dow_30_2009_2020.csv' to adjust the value...

kaveh6202

Fix cost

Hi, if the ```abs(action)=100 > self.state[index+STOCK_DIM+1]=110```, the cost at this step will be 0 because the ```state[index+STOCK_DIM+1]``` is updated before cost calculation. ``` self.state[index+STOCK_DIM+1] -= min(abs(action), self.state[index+STOCK_DIM+1]) self.cost +=self.state[index+1]*min(abs(action),self.state[index+STOCK_DIM+1]) *...

ydup

improve model

thanks for you amazing article , is there new update for this model to be published , whats your tips to improve this model

saeed-4810

hyperparameter tuning

1

hey sir thanks for your helpful documentation I have a question and i was wondering if yo could answer have you tried hyperparameter tuning like bayesian optimization and why you...

saeed-4810

What is StockTradingRLEnv.StockEnv for?

3

HI @BruceYanghy as you know I'm expanding your work for my masters thesis. And for that, I stepped over the following class: [StockEnv](https://github.com/AI4Finance-LLC/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020/blob/master/env/StockTradingRLEnv.py) As far as I scanned over the...

Pit-Storm

Integrate with current CNN model

Hi Bruce, Undoubtedly this is a great contribution to DRL Stock Trading by you. I am new to DRL so it will be a great help if you clear my...

ankit-crossml

docker-image

2

Nice work! it's possible create an docker image?

igorpereirabr1

turbulence_threshold

2

Hi, I'm following your great work :-) , and in models.py, I came across turbulence_threshold, can you please explain how did you calculate the turbulence_threshold to be 140, 100, 90...

NethanelK