Reinforcement learning versus supervised learning

A lot of current research is focused on supervised learning. Reinforcement learning might seem a bit similar to supervised learning, but it is not. The process of supervised learning refers to learning from labeled samples provided by us. While this is a very useful technique, it is not sufficient to start learning from interactions. When we want to design a machine to navigate unknown terrains, this kind of learning is not going to help us. We don't have training samples available beforehand. We need an agent that can learn from its own experience by interacting with the unknown terrain. This is where reinforcement learning really shines.

Let's consider the exploration part where the agent has to interact with the new environment in order to learn. How much can it possibly explore? We do not even know how big the environment is, and in most cases, it is not possible to explore all the possibilities. So what should the...