We combined books and research papers to create a knowledge base. We then used that to create a research program to check if they can be applied to Indian stocks/futures for profit. Our threshold for success was outperformance against naive momentum/trend strategies. RL implementations tend to be complicated and compute intensive. They least they can do is beat simple systems. Also, India is an expensive venue to trade so these tests included those costs as well.
Across every reward, cost, state, action, algorithm, universe, and venue we tried, no RL agent beat classical baselines net of costs out-of-sample.
Our research plan, and eli5 are good places to start. Or, you can jump right into the summary of the results.
This is by no means exhaustive and we chose simple RL systems to get our beaks wet. However, the lack of WOW! is concerning.
Code, charts, etc. are on github.