rl-fin / README.md
bonadio's picture
qlearning_v1-6 using PRB reward
7cf1db5
|
raw
history blame
256 Bytes
metadata
{}

This is what we learned on HF RL Unit1 adjusted to use crypto market data

Model result

Q-learning

Now using q-learnig with a custom enviroment fin_rl_qlearning_v1.ipynb