Reinforcement Learning Algorithms with Python

The algorithm

Basically, all the observations we have done for the TD update are also valid for SARSA. Once we apply them to the definition of Q-function, we obtain the SARSA update:

is a coefficient that determines how much the action value has been updated. is the discount factor, a coefficient between 0 and 1 used to give less importance to the values that come from distant future decisions (short-term actions are preferred to long-term ones). ...