Which of the following is$/$are false regarding reinforcement learning?

Reinforcement learning is also same as unsupervised learning. as we map inputs to ouputs n unsupervised learn

i$)$ in$,$ reinforcement learning actons are taken abased on the policy such that the reward is maximum.

IIT$)$ Most of the times, explotation approach provides optimal resiat than Exploraticn approach in reinforcement lean

M$)$ in$,$ renforcement learning, the model learns continualy, unike supervised learning.

I and N

II and $N$

It and N

enly it