training_ml_control.environments.cart

Original code taken from: Farama-Foundation/Gymnasium

MIT License: Farama-Foundation/Gymnasium

Module Contents

Classes

CartEnv

The cart, or double-integarator, problem is based on the classic problem in control theory. It is a simple cart that can move without friction to the left or to the right.

Data

__all__
logger

API

training_ml_control.environments.cart.__all__

[‘CartEnv’]

training_ml_control.environments.cart.logger

‘getLogger(…)’

class training_ml_control.environments.cart.CartEnv(render_mode: str | None = None, *, goal_velocity: float = 5, max_position: float = 200, max_speed: float = 10, max_force: float = 10, goal_position: float = 9.0)

Bases: gymnasium.envs.classic_control.continuous_mountain_car.Continuous_MountainCarEnv

The cart, or double-integarator, problem is based on the classic problem in control theory. It is a simple cart that can move without friction to the left or to the right.

\[\begin{split} \begin{array}{ll} \ddot {q} &= u(t)\\ y &= q(t) \end{array} \end{split}\]

where \(\displaystyle q(t),u(t)\in \mathbb {R}\).

This class is a modified version of the Continuous_MountainCarEnv environment from gymnasium that modifies that environment to be flat.

Initialization

_height(xs: numpy.typing.NDArray) → numpy.typing.NDArray

step(action: numpy.typing.NDArray) → tuple[numpy.typing.NDArray, float, bool, bool, dict]

render()