Reinforcement Learning (AD-802 (B)) - Important Questions

Define reinforcement learning and give a real-life example.

Explain various approaches to implement reinforcement learning.

Differentiate between reinforcement learning and supervised learning.

Explain Median Elimination, Upper Confidence Bound (UCB) algorithm, and Probably Approximately Correct (PAC) with respect to bandit algorithms.

What is the key objective of bandit algorithms in reinforcement learning?

Given pull counts $n_a$ and estimates $Q_t(a)$ after $t$ iterations, which arm should UCB1 play next?

What is meant by passive and active reinforcement learning and how do we compare the two?

Explain the Q-Function and Q-Learning Algorithm.

Discuss Maximum Likelihood and Least Square Error Hypothesis.

Explain the following.

Explain Fitted-Q and Deep Q-Learning Problems.

Explain any one advanced Q-learning algorithms.

Explain learning policies by imitating optimal controllers.

Explain inverse reinforcement learning.