You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
First of all, thank you for providing the excellent tutorials and open-source implementations in FinRL — they are very helpful for reinforcement learning applications in finance!
I have a question regarding the notebook:
📍 FinRL-Tutorials/5-Others/tutorial_this_works_1_18.ipynb
Specifically in:
Part 5. Design Environment → class StockTradingEnvV2(gym.Env)
In the step(self, actions) function, I noticed the following line:
"actions = actions / closings"
Could you kindly explain the purpose of this line?
Is it intended to normalize the action values by the stock's closing prices?
Or does it serve a different function related to position sizing, portfolio allocation, or transaction cost handling?
I’d appreciate any clarification you could provide.