QuizMe

* השאלה נוספה בתאריך: 28-02-2025

		a) Environments with sparse rewards, where the reward is sparse or delayed
		b) Environments with frequent rewards (i.e., almost every action yields a reward)
		c) Environments that require a great deal of exploration
		d) Environments with high stochasticity in state transitions

10. [General] In which of the following setups, Sarsa is likely to outperform Q-learning (multiple answers may apply):