I'd like to solve Open AI's 'taxi-v2' or 'taxi-v3' environment using MONTE CARLO CONTROL agent.
I need Q-Learning and MC Control and I've solved Q-Learning but couldn't solve MC Control.
Just make sure that I only need MC Control (not MC Predict/TD/DQN/SALSA and so on)
I have a test code so you can test with your code.
The environment is ready so all I need is to code value/Q function.
If you are interested in this project, please message me:)
Hi, I am a computer science in the Istanbul Technical University and I'm interested in reinforcement learning for 2 years and I can surely help you on that!