I decided to start this project here after I failed to complete a similar project on time. And also failed to achieve the results I wanted.
So, as the name suggests, it's just a project that applies reinforcement learning to the trading problem. This time, I want to achieve good results. And since I don't have a deadline, that won't be a problem for now.
It's also important to mention that in my first attempt, I was writing a paper about it, so the project won't be just code.
In fact, looking back now, jumping straight into the code was one of the mistakes I made when developing the project. So, for this new attempt, before I start coding, I'll do a good literature review and write a good theoretical background.