In the Taxonomy of RL methods section in Chapter 4, The Cross-Entropy Method, we saw several different angles we can classify RL methods from. We distinguished three main aspects:
Value-based and policy-based
On-policy and off-policy
Model-free and model-based
There were enough examples of methods on both sides of the first and the second categories, but all the methods we've seen so far were 100% model-free. This doesn't mean that model-free methods are more important or better than their model-based antagonists. Historically, due to their sample-efficiency, the model-based methods have been used in the robotics field and other industrial controls. That is happened due to the cost of the hardware and the physical limitations of samples that could be obtained from a real robot. Robots with a large amount of degrees of freedom are not widely accessible, so RL researchers are more focused on computer games and other environments where samples are relatively cheap...