Environments, similar to labeled datasets in supervised learning, are the essential part of RL as they dictate the information that has to be learned and the choice of algorithms. In this section, we'll take a look at the main differences between the types of environments and list some of the most important open source environments.
Types of RL environments
Why different environments?
While, for real applications, the choice of environment is dictated by the task to be learned, for research applications, usually, the choice is dictated by intrinsic features of the environment. In this latter case, the end goal is not to train the agent on a specific task, but to show some task-related capabilities.
For instance, if the...