In this chapter, we explored the list of Gym environments available on your system, which you installed in the previous chapter, and then understood the naming conventions, or nomenclature, of the environments. We then revisited the agent-environment interaction (the RL loop) diagram and understood how the Gym environment provides the interfaces corresponding to each of the arrows we saw in the image. We then looked at a consolidated summary of the four values returned by the Gym environment's step() method in a tabulated, easy-to-understand format to reinforce your understanding of what they mean!
We also explored in detail the various types of spaces used in the Gym for the observation and action spaces, and we used a script to print out what spaces are used by an environment to understand the Gym environment interfaces better. In our next chapter, we will consolidate...
