Summary

In this chapter, we've covered MAB problems, which is one-step reinforcement learning with many practical business applications. Despite its apparent simplicity, it is tricky to balance the exploration and exploitation in MAB problems, and any improvements in managing this trade-off comes with savings in costs and increases in revenue. We have introduced four approaches to this end: A/B/n testing, ε-greedy actions, action selection using upper confidence bounds and Thompson sampling. We implemented these approaches in an online advertising scenario and discussed their advantages and disadvantages.

So far, while making decisions, we have not considered any information about the situation in the environment. For example, we have not used any information about the users (e.g. location, age, previous behavior etc.) in the online advertising scenario that could be available to our decision-making algorithm. In the next chapter, you will learn about a more advanced...