Python Deep Learning Projects

SARSA learning

SARSA learning, like Q-learning, is also a policy-based reinforcement learning technique. Its goal is to learn an optimal policy, which helps an agent decide on the action that needs to be taken under various possible circumstances.

SARSA and Q-learning are very similar to each other, except Q-learning is an off-policy algorithm and SARSA is an on-policy algorithm. The Q value learned by SARSA is not based on a greedy policy like in Q-learning but is based on the action performed under the current  policy.

For a single state, s, and an action, a, Q(s, a) can be expressed in terms of the Q value of the next state, s' ,and action, a', given by the following formula:

The following is the pseudocode for the SARSA learning algorithm ...