Chapter 6 – Case Study – The MAB Problem
- The Multi-Armed Bandit (MAB) problem is one of the classic problems in RL. A MAB is a slot machine where we pull the arm (lever) and get a payout (reward) based on some probability distribution. A single slot machine is called a one-armed bandit, and when there are multiple slot machines, it is called a MAB or k-armed bandit, where k denotes the number of slot machines.
- With the epsilon-greedy policy, we select the best arm with probability 1-epsilon, and we select the random arm with probability epsilon.
- In softmax exploration, the arm will be selected based on the probability. However, in the initial rounds we will not know the correct average reward of each arm, so selecting the arm based on the probability of average reward will be inaccurate in the initial rounds. So to avoid this we introduce a new parameter called T. T is called the temperature parameter.
- The upper confidence bound is computed...