Environment synopsis

We have learned about several types of Gym environment. Wouldn't it be nice if we could have information about all the environments in a single place? Yes! The Gym wiki provides a description of all the environments with their environment id, state space, action space, and reward range in a table: https://github.com/openai/gym/wiki/Table-of-environments.

We can also check all the available environments in Gym using the registry.all() method:

from gym import envs
print(envs.registry.all())

The preceding code will print all the available environments in Gym.

Thus, in this chapter, we have learned about the Gym toolkit and also several interesting environments offered by Gym. In the upcoming chapters, we will learn how to train our RL agent in a Gym environment to find the optimal policy.