Getting Started¶

Making an environment¶

Here is a quick example of how to create an environment:

All the environments¶

The following is a list of all the environments available and their descriptions:

Flyer
Trajectory
Runway
Forced Landing

Configuring an environment¶

The observations, actions, dynamics and rewards of an environment are parametrized by the configuration config dictionary. After environment creation, the configuration can be accessed using the {py:attr} ~flyer_env.envs.common.abstract.AbstractEnv.config attribute.

Note

The environment must be reset() for the change in configuration to have effect.

Training an agent¶

Here is an example using … to train … with default kinematics and an MLP model.