שאלה | 7. [Imitation learning] Which of the following IS NOT an advantage of behavior cloning compared to reinforcement learning (multiple answers may apply)?

7. [Imitation learning] Which of the following IS NOT an advantage of behavior cloning compared to reinforcement learning (multiple answers may apply)?

		a) Removes the need to design a reward function that is task-specific
		b) Removes the need for hand-designed features for state representation
		c) Removes the need for long-horizon planning
		d) Avoids a problem known as “reward hacking”, where the RL agent learns to maximize the reward function (e.g., an endless loop) instead of learning the desired behavior