gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-08-23 15:04:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Clean up mountain car environment (#1961)

Browse Source 
* Clean up mountain car environment.

* Add whitespace around division operator.
This commit is contained in:
InstanceLabs
2020-06-19 23:13:15 +02:00
committed by GitHub
parent abef916ca2
commit d4e596bf65
1 changed files with 52 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
gym/envs/classic_control/mountain_car.py
View File

@@ -2,7 +2,6 @@
http://incompleteideas.net/sutton/MountainCar/MountainCar1.cp http://incompleteideas.net/sutton/MountainCar/MountainCar1.cp
permalink: https://perma.cc/6Z2N-PFWC permalink: https://perma.cc/6Z2N-PFWC
""" """
import math import math
import numpy as np import numpy as np
@@ -11,6 +10,7 @@ import gym
from gym import spaces from gym import spaces
from gym.utils import seeding from gym.utils import seeding
class MountainCarEnv(gym.Env): class MountainCarEnv(gym.Env):
""" """
Description: Description:
@@ -47,33 +47,39 @@ class MountainCarEnv(gym.Env):
[-0.6 , -0.4]. [-0.6 , -0.4].
The starting velocity of the car is always assigned to 0. The starting velocity of the car is always assigned to 0.
Episode Termination: Episode Termination:
The car position is more than 0.5 The car position is more than 0.5
Episode length is greater than 200 Episode length is greater than 200
""" """
metadata = { metadata = {
'render.modes': ['human', 'rgb_array'], 'render.modes': ['human', 'rgb_array'],
'video.frames_per_second': 30 'video.frames_per_second': 30
} }
def __init__(self, goal_velocity = 0): def __init__(self, goal_velocity=0):
self.min_position = -1.2 self.min_position = -1.2
self.max_position = 0.6 self.max_position = 0.6
self.max_speed = 0.07 self.max_speed = 0.07
self.goal_position = 0.5 self.goal_position = 0.5
self.goal_velocity = goal_velocity self.goal_velocity = goal_velocity
self.force=0.001
self.gravity=0.0025
self.low = np.array([self.min_position, -self.max_speed], dtype=np.float32) self.force = 0.001
self.high = np.array([self.max_position, self.max_speed], dtype=np.float32) self.gravity = 0.0025
self.low = np.array(
[self.min_position, -self.max_speed], dtype=np.float32
)
self.high = np.array(
[self.max_position, self.max_speed], dtype=np.float32
)
self.viewer = None self.viewer = None
self.action_space = spaces.Discrete(3) self.action_space = spaces.Discrete(3)
self.observation_space = spaces.Box(self.low, self.high, dtype=np.float32) self.observation_space = spaces.Box(
self.low, self.high, dtype=np.float32
)
self.seed() self.seed()
@@ -85,13 +91,16 @@ class MountainCarEnv(gym.Env):
assert self.action_space.contains(action), "%r (%s) invalid" % (action, type(action)) assert self.action_space.contains(action), "%r (%s) invalid" % (action, type(action))
position, velocity = self.state position, velocity = self.state
velocity += (action-1)*self.force + math.cos(3*position)*(-self.gravity) velocity += (action - 1) * self.force + math.cos(3 * position) * (-self.gravity)
velocity = np.clip(velocity, -self.max_speed, self.max_speed) velocity = np.clip(velocity, -self.max_speed, self.max_speed)
position += velocity position += velocity
position = np.clip(position, self.min_position, self.max_position) position = np.clip(position, self.min_position, self.max_position)
if (position==self.min_position and velocity<0): velocity = 0 if (position == self.min_position and velocity < 0):
velocity = 0
done = bool(position >= self.goal_position and velocity >= self.goal_velocity) done = bool(
position >= self.goal_position and velocity >= self.goal_velocity
)
reward = -1.0 reward = -1.0
self.state = (position, velocity) self.state = (position, velocity)
@@ -102,24 +111,23 @@ class MountainCarEnv(gym.Env):
return np.array(self.state) return np.array(self.state)
def _height(self, xs): def _height(self, xs):
return np.sin(3 * xs)*.45+.55 return np.sin(3 * xs) * .45 + .55
def render(self, mode='human'): def render(self, mode='human'):
screen_width = 600 screen_width = 600
screen_height = 400 screen_height = 400
world_width = self.max_position - self.min_position world_width = self.max_position - self.min_position
scale = screen_width/world_width scale = screen_width / world_width
carwidth=40 carwidth = 40
carheight=20 carheight = 20
if self.viewer is None: if self.viewer is None:
from gym.envs.classic_control import rendering from gym.envs.classic_control import rendering
self.viewer = rendering.Viewer(screen_width, screen_height) self.viewer = rendering.Viewer(screen_width, screen_height)
xs = np.linspace(self.min_position, self.max_position, 100) xs = np.linspace(self.min_position, self.max_position, 100)
ys = self._height(xs) ys = self._height(xs)
xys = list(zip((xs-self.min_position)*scale, ys*scale)) xys = list(zip((xs - self.min_position) * scale, ys * scale))
self.track = rendering.make_polyline(xys) self.track = rendering.make_polyline(xys)
self.track.set_linewidth(4) self.track.set_linewidth(4)
@@ -127,40 +135,49 @@ class MountainCarEnv(gym.Env):
clearance = 10 clearance = 10
l,r,t,b = -carwidth/2, carwidth/2, carheight, 0 l, r, t, b = -carwidth / 2, carwidth / 2, carheight, 0
car = rendering.FilledPolygon([(l,b), (l,t), (r,t), (r,b)]) car = rendering.FilledPolygon([(l, b), (l, t), (r, t), (r, b)])
car.add_attr(rendering.Transform(translation=(0, clearance))) car.add_attr(rendering.Transform(translation=(0, clearance)))
self.cartrans = rendering.Transform() self.cartrans = rendering.Transform()
car.add_attr(self.cartrans) car.add_attr(self.cartrans)
self.viewer.add_geom(car) self.viewer.add_geom(car)
frontwheel = rendering.make_circle(carheight/2.5) frontwheel = rendering.make_circle(carheight / 2.5)
frontwheel.set_color(.5, .5, .5) frontwheel.set_color(.5, .5, .5)
frontwheel.add_attr(rendering.Transform(translation=(carwidth/4,clearance))) frontwheel.add_attr(
rendering.Transform(translation=(carwidth / 4, clearance))
)
frontwheel.add_attr(self.cartrans) frontwheel.add_attr(self.cartrans)
self.viewer.add_geom(frontwheel) self.viewer.add_geom(frontwheel)
backwheel = rendering.make_circle(carheight/2.5) backwheel = rendering.make_circle(carheight / 2.5)
backwheel.add_attr(rendering.Transform(translation=(-carwidth/4,clearance))) backwheel.add_attr(
rendering.Transform(translation=(-carwidth / 4, clearance))
)
backwheel.add_attr(self.cartrans) backwheel.add_attr(self.cartrans)
backwheel.set_color(.5, .5, .5) backwheel.set_color(.5, .5, .5)
self.viewer.add_geom(backwheel) self.viewer.add_geom(backwheel)
flagx = (self.goal_position-self.min_position)*scale flagx = (self.goal_position-self.min_position) * scale
flagy1 = self._height(self.goal_position)*scale flagy1 = self._height(self.goal_position) * scale
flagy2 = flagy1 + 50 flagy2 = flagy1 + 50
flagpole = rendering.Line((flagx, flagy1), (flagx, flagy2)) flagpole = rendering.Line((flagx, flagy1), (flagx, flagy2))
self.viewer.add_geom(flagpole) self.viewer.add_geom(flagpole)
flag = rendering.FilledPolygon([(flagx, flagy2), (flagx, flagy2-10), (flagx+25, flagy2-5)]) flag = rendering.FilledPolygon(
flag.set_color(.8,.8,0) [(flagx, flagy2), (flagx, flagy2 - 10), (flagx + 25, flagy2 - 5)]
)
flag.set_color(.8, .8, 0)
self.viewer.add_geom(flag) self.viewer.add_geom(flag)
pos = self.state[0] pos = self.state[0]
self.cartrans.set_translation((pos-self.min_position)*scale, self._height(pos)*scale) self.cartrans.set_translation(
(pos-self.min_position) * scale, self._height(pos) * scale
)
self.cartrans.set_rotation(math.cos(3 * pos)) self.cartrans.set_rotation(math.cos(3 * pos))
return self.viewer.render(return_rgb_array = mode=='rgb_array') return self.viewer.render(return_rgb_array=mode == 'rgb_array')
def get_keys_to_action(self): def get_keys_to_action(self):
return {():1,(276,):0,(275,):2,(275,276):1} #control with left and right arrow keys # Control with left and right arrow keys.
return {(): 1, (276,): 0, (275,): 2, (275, 276): 1}
def close(self): def close(self):
if self.viewer: if self.viewer:
self.viewer.close() self.viewer.close()