Hands-On Intelligent Agents with OpenAI Gym

Registering custom environments with OpenAI Gym

The registration of a custom Gym environment is easy with the use of the gym.envs.registration.register module; this provides the register method, which in turn takes as an argument id, which is the name of the environment we want to use when calling gym.make(...) and entry_point , the class name for the custom environment implementation we discussed earlier. The code snippet to register the CustomEnv class we implemented is as follows:

from gym.envs.registration import registerregister(    id='CustomEnv-v0',    entry_point='custom_environments.envs:CustomEnv',)

We will make use of this template later on in this chapter to create a custom Gym environment that uses a very sophisticated driving simulator. ...