We started off the chapter by understanding what the MAB problem is and how it can be solved using several exploration strategies. We first learned about the epsilon-greedy method, where we select a random arm with a probability epsilon and select the best arm with a probability 1-epsilon. Next, we learned about the softmax exploration method, where we select the arm based on the probability distribution, and the probability of each arm is proportional to the average reward.
Following this, we learned about the UCB algorithm, where we select the arm that has the highest upper confidence bound. Then, we explored the Thomspon sampling method, where we learned the distributions of the arms based on the beta distribution.
Moving forward, we learned how MAB can be used as an alternative to AB testing and how can we find the best advertisement banner by framing the problem as a MAB problem. At the end of the chapter, we also had an overview of contextual bandits.