SARSA Algorithm and Q-Learning

Front

What is the SARSA algorithm a variation of?

Back

The popular Q-Learning algorithm.

Front

What are the two types of policies in Reinforcement Learning?

Back

On Policy and Off Policy.

Front

What does On Policy mean in Reinforcement Learning?

Back

The learning agent learns the value function according to the current action derived from the policy currently being used.

Front

What does Off Policy mean in Reinforcement Learning?

Back

The learning agent learns the value function according to the action derived from another policy.

Front

What type of technique is Q-Learning?

Back

Off Policy technique.

Front

What approach does Q-Learning use to learn the Q-value?

Back

The greedy approach.

Front

What type of technique is SARSA?

Back

On Policy technique.

Front

How does SARSA learn the Q-value?

Back

It uses the action performed by the current policy.

Front

What is the update statement for Q-Learning?

Back

Q(s_{t},a_{t}) = Q(s_{t},a_{t}) + α (r_{t+1}+γ max_{a}Q(s_{t+1},a)-Q(s_{t},a_{t}))

Front

What is the update statement for SARSA?

Back

Q(s_{t},a_{t}) = Q(s_{t},a_{t}) + α (r_{t+1}+γ Q(s_{t+1},a_{t+1})-Q(s_{t},a_{t}))