So, I’ve been very active this two days and managed to implement SARSA algorithm for solving Taxi-v2.
They look mostly the same except that in Q-learning, we update our Q-function by assuming we are taking action `a` that maximises our post-state Q function.
In SARSA, we use the same policy that generated the previous action a to generate the next action, `a-prim`, which we run through our Q-function for updates.
I have managed to reach the same score as with Q-learning in about the same time. I guess Taxi-v2 problem is solved once an forever.