Implementation of RL algorithm Rmax in Python.
Strongly based (if not plainly copied) from https://github.com/jmacglashan/burlap (the real deal)
It is supposed to be based on Burlap's Tabular Rmax model, with support for any number of players (instead of a MDP's context).
Yet, very naive attempt with educational purposes.
Check also https://github.com/david-abel/simple_rl