QuizMe

* השאלה נוספה בתאריך: 26-02-2025

		The policy we aim to learn is not the one used to generate the data
		Off-policy methods always require that we sample an entire trajectory prior to updating the target policy
		Importance sampling is used to bridge the gap between the target and behaviour policy
		The behaviour policy in trajectory X is the target policy in trajectory X-1

Which of the following statements are correct regarding off-policy methods (multiple answers may apply)