Gymnasium/gym/envs/classic_control/continuous_mountain_car.py

"""
@author: Olivier Sigaud

A merge between two sources:

* Adaptation of the MountainCar Environment from the "FAReinforcement" library
of Jose Antonio Martin H. (version 1.0), adapted by  'Tom Schaul, tom@idsia.ch'
and then modified by Arnaud de Broissia

* the gym MountainCar environment
itself from
http://incompleteideas.net/sutton/MountainCar/MountainCar1.cp
permalink: https://perma.cc/6Z2N-PFWC
"""

import math
from typing import Optional

import numpy as np

import gym
from gym import spaces
from gym.utils import seeding


class Continuous_MountainCarEnv(gym.Env):
    """
    The agent (a car) is started at the bottom of a valley. For any given state
    the agent may choose to accelerate to the left, right or cease any
    acceleration. The code is originally based on [this code](http://incompleteideas.net/MountainCar/MountainCar1.cp)
    and the environment appeared first in Andrew Moore's PhD Thesis (1990):
    ```
    @TECHREPORT{Moore90efficientmemory-based,
        author = {Andrew William Moore},
        title = {Efficient Memory-based Learning for Robot Control},
        institution = {},
        year = {1990}
    }
    ```

    ## Observation Space

    The observation space is a 2-dim vector, where the 1st element represents the "car position" and the 2nd element represents the "car velocity".

    ## Action

    The actual driving force is calculated by multiplying the power coef by power (0.0015)

    ## Reward

    Reward of 100 is awarded if the agent reached the flag (position = 0.45)
    on top of the mountain. Reward is decrease based on amount of energy consumed each step.

    ## Starting State

    The position of the car is assigned a uniform random value in [-0.6 , -0.4]. The starting velocity of the car is always assigned to 0.

    ## Episode Termination

    The car position is more than 0.45. Episode length is greater than 200

    ## Arguments

    ```
    gym.make('MountainCarContinuous-v0')
    ```

    ## Version History

    * v0: Initial versions release (1.0.0)
    """

    metadata = {"render.modes": ["human", "rgb_array"], "video.frames_per_second": 30}

    def __init__(self, goal_velocity=0):
        self.min_action = -1.0
        self.max_action = 1.0
        self.min_position = -1.2
        self.max_position = 0.6
        self.max_speed = 0.07
        self.goal_position = (
            0.45  # was 0.5 in gym, 0.45 in Arnaud de Broissia's version
        )
        self.goal_velocity = goal_velocity
        self.power = 0.0015

        self.low_state = np.array(
            [self.min_position, -self.max_speed], dtype=np.float32
        )
        self.high_state = np.array(
            [self.max_position, self.max_speed], dtype=np.float32
        )

        self.viewer = None

        self.action_space = spaces.Box(
            low=self.min_action, high=self.max_action, shape=(1,), dtype=np.float32
        )
        self.observation_space = spaces.Box(
            low=self.low_state, high=self.high_state, dtype=np.float32
        )

    def step(self, action):

        position = self.state[0]
        velocity = self.state[1]
        force = min(max(action[0], self.min_action), self.max_action)

        velocity += force * self.power - 0.0025 * math.cos(3 * position)
        if velocity > self.max_speed:
            velocity = self.max_speed
        if velocity < -self.max_speed:
            velocity = -self.max_speed
        position += velocity
        if position > self.max_position:
            position = self.max_position
        if position < self.min_position:
            position = self.min_position
        if position == self.min_position and velocity < 0:
            velocity = 0

        # Convert a possible numpy bool to a Python bool.
        done = bool(position >= self.goal_position and velocity >= self.goal_velocity)

        reward = 0
        if done:
            reward = 100.0
        reward -= math.pow(action[0], 2) * 0.1

        self.state = np.array([position, velocity], dtype=np.float32)
        return self.state, reward, done, {}

    def reset(self, *, seed: Optional[int] = None, options: Optional[dict] = None):
        super().reset(seed=seed)
        self.state = np.array([self.np_random.uniform(low=-0.6, high=-0.4), 0])
        return np.array(self.state, dtype=np.float32)

    def _height(self, xs):
        return np.sin(3 * xs) * 0.45 + 0.55

    def render(self, mode="human"):
        screen_width = 600
        screen_height = 400

        world_width = self.max_position - self.min_position
        scale = screen_width / world_width
        carwidth = 40
        carheight = 20

        if self.viewer is None:
            from gym.utils import pyglet_rendering

            self.viewer = pyglet_rendering.Viewer(screen_width, screen_height)
            xs = np.linspace(self.min_position, self.max_position, 100)
            ys = self._height(xs)
            xys = list(zip((xs - self.min_position) * scale, ys * scale))

            self.track = pyglet_rendering.make_polyline(xys)
            self.track.set_linewidth(4)
            self.viewer.add_geom(self.track)

            clearance = 10

            l, r, t, b = -carwidth / 2, carwidth / 2, carheight, 0
            car = pyglet_rendering.FilledPolygon([(l, b), (l, t), (r, t), (r, b)])
            car.add_attr(pyglet_rendering.Transform(translation=(0, clearance)))
            self.cartrans = pyglet_rendering.Transform()
            car.add_attr(self.cartrans)
            self.viewer.add_geom(car)
            frontwheel = pyglet_rendering.make_circle(carheight / 2.5)
            frontwheel.set_color(0.5, 0.5, 0.5)
            frontwheel.add_attr(
                pyglet_rendering.Transform(translation=(carwidth / 4, clearance))
            )
            frontwheel.add_attr(self.cartrans)
            self.viewer.add_geom(frontwheel)
            backwheel = pyglet_rendering.make_circle(carheight / 2.5)
            backwheel.add_attr(
                pyglet_rendering.Transform(translation=(-carwidth / 4, clearance))
            )
            backwheel.add_attr(self.cartrans)
            backwheel.set_color(0.5, 0.5, 0.5)
            self.viewer.add_geom(backwheel)
            flagx = (self.goal_position - self.min_position) * scale
            flagy1 = self._height(self.goal_position) * scale
            flagy2 = flagy1 + 50
            flagpole = pyglet_rendering.Line((flagx, flagy1), (flagx, flagy2))
            self.viewer.add_geom(flagpole)
            flag = pyglet_rendering.FilledPolygon(
                [(flagx, flagy2), (flagx, flagy2 - 10), (flagx + 25, flagy2 - 5)]
            )
            flag.set_color(0.8, 0.8, 0)
            self.viewer.add_geom(flag)

        pos = self.state[0]
        self.cartrans.set_translation(
            (pos - self.min_position) * scale, self._height(pos) * scale
        )
        self.cartrans.set_rotation(math.cos(3 * pos))

        return self.viewer.render(return_rgb_array=mode == "rgb_array")

    def close(self):
        if self.viewer:
            self.viewer.close()
            self.viewer = None