Reinforcement Learning Algorithms with Python

A broad perspective on model-based learning

Let's first remember what a model is. A model consists of the transition dynamics and rewards of an environment. Transition dynamics are a mapping from a state, s, and an action, a, to the next state, s'.

Having this information, the environment is fully represented by the model that can be used in its place. And if an agent has access to it, then the agent has the ability to predict its own future.

In the following sections, we'll see that a model can be either known or unknown. In the former case, the model is used as it is to exploit the dynamics of the environment; that is, the model provides a representation that is used in place of the environment. In the latter case, where the model of the ...