This is a repository where I'll be uploading my attempts at writing RL code. Hopefully, they will be compatible with OpenAI's Gym environments, so that they may be easily tested in "real" or at least stanard environments.
So far, we have only policy evaluation methods:
- Monte Carlo State and Action Value function approximation
- TD(0) State and Action Value function approximation
- TD(lambda) State and Action Value function approximation