A$)$ Explain the key concepts behind Tabular$-$based Reinforcement Learning. How does it update value SHTestimates and what are its limitations$?[2\mathrm{.}5$ Marks$)$

B$)$ Compare Behavioral Cloning and Imitation Learning. Describe how each approach learns from demonstrations and explain the key differences between them. Provide a discussion on their advantages and disadvantages in the context of training