SARSA follows an on-policy learning algorithm or an off-policy learning algorithm?

Reinforcement Learning - Quiz(MCQ)

On-policy

Off-policy

Both (A) and (B)

None of the above

Correct Answer : On-policy

Explanation : SARSA is based upon an on-policy learning algorithm.

Recently Updated in Reinforcement Learning Questions

Gamma (Î³) in the bellman equation is known as?

Value factor

Discount factor

Environment factor

None of the above

Correct Answer : Discount factor

Explanation : Gamma (γ) in the bellman equation is known as the Discount factor.

How do you represent the agent state in reinforcement learning?

Markov state

Discount state

Discount factor

None of the above

Correct Answer : Markov state

Explanation : Represent the agent state in reinforcement learning Markov state.

P[St+1 | St ] = P[St +1 | S1,......, St], in this condition
What is the meaning of St?

State factor

Markov state

Discount factor

None of the above

Correct Answer : Markov state

Explaination : P[St+1 | St ] = P[St +1 | S1,......, St], in the following condition St represents the Markov state.

New Technologies MCQ's

Machine Learning

Artificial Intelligence