gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-09-03 02:52:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add mild domain randomization to Car Racing Env (#2749)

Browse Source 
* first commit domain randomize

* black

* update doc

* add some type hints and internalized some functions

* we were told, the black bear is innocent; but I should not like to trust
myself wit him

* Don't need two color conventions

* don't multiply twice

* hardcore -> domain_randomize & register

* remove rogue decorator
This commit is contained in:
Jet
2022-04-15 16:04:24 +01:00
committed by GitHub
parent 681a99296e
commit c6deb81ad3
3 changed files with 65 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
gym/envs/__init__.py
View File

@@ -89,6 +89,14 @@ register(
reward_threshold=900,
)
register(
id="CarRacingDomainRandomize-v1",
entry_point="gym.envs.box2d:CarRacing",
kwargs={"domain_randomize": True},
max_episode_steps=1000,
reward_threshold=900,
)
# Toy Text
# ----------------------------------------

82
gym/envs/box2d/car_racing.py
View File

@@ -34,8 +34,6 @@ TRACK_WIDTH = 40 / SCALE
BORDER = 8 / SCALE
BORDER_MIN_COUNT = 4
ROAD_COLOR = [0.4, 0.4, 0.4]
class FrictionDetector(contactListener):
def __init__(self, env, lap_complete_percent):
@@ -63,9 +61,8 @@ class FrictionDetector(contactListener):
if not tile:
return
tile.color[0] = ROAD_COLOR[0]
tile.color[1] = ROAD_COLOR[1]
tile.color[2] = ROAD_COLOR[2]
# inherit tile color from env
tile.color = self.env.norm_road_color / 255
if not obj or "tiles" not in obj.__dict__:
return
if begin:
@@ -128,10 +125,15 @@ class CarRacing(gym.Env, EzPickle):
receive -100 reward and die.
### Arguments
There are no arguments supported in constructing the environment.
`lap_complete_percent` dictates the percentage of tiles that must be visited by
the agent before a lap is considered complete.
Passing `domain_randomize=True` enabled the domain randomized variant of the environment.
In this scenario, the background and track colours are different on every reset.
### Version History
- v0: Current version
- v1: Current version (0.24.0)
- v0: Original version
### References
- Chris Campbell (2014), http://www.iforce2d.net/b2dtut/top-down-car.
@@ -145,8 +147,16 @@ class CarRacing(gym.Env, EzPickle):
"render_fps": FPS,
}
def __init__(self, verbose=1, lap_complete_percent=0.95):
def __init__(
self,
verbose: bool = True,
lap_complete_percent: float = 0.95,
domain_randomize: bool = False,
):
EzPickle.__init__(self)
self.domain_randomize = domain_randomize
self._init_colors()
self.contactListener_keepref = FrictionDetector(self, lap_complete_percent)
self.world = Box2D.b2World((0, 0), contactListener=self.contactListener_keepref)
self.screen = None
@@ -183,6 +193,22 @@ class CarRacing(gym.Env, EzPickle):
self.road = []
self.car.destroy()
def _init_colors(self):
if self.domain_randomize:
# domain randomize the bg and grass colour
self.norm_road_color = self.np_random.uniform(0, 210, size=3)
self.bg_color = self.np_random.uniform(0, 210, size=3)
self.grass_color = np.copy(self.bg_color)
idx = self.np_random.integers(3)
self.grass_color[idx] += 20
else:
# default colours
self.norm_road_color = np.array([102, 102, 102])
self.bg_color = np.array([102, 204, 102])
self.grass_color = np.array([102, 230, 102])
def _create_track(self):
CHECKPOINTS = 12
@@ -280,7 +306,7 @@ class CarRacing(gym.Env, EzPickle):
elif pass_through_start and i1 == -1:
i1 = i
break
if self.verbose == 1:
if self.verbose:
print("Track generation: %i..%i -> %i-tiles track" % (i1, i2, i2 - i1))
assert i1 != -1
assert i2 != -1
@@ -338,8 +364,8 @@ class CarRacing(gym.Env, EzPickle):
self.fd_tile.shape.vertices = vertices
t = self.world.CreateStaticBody(fixtures=self.fd_tile)
t.userData = t
c = 0.01 * (i % 3)
t.color = [ROAD_COLOR[0] + c, ROAD_COLOR[1] + c, ROAD_COLOR[2] + c]
c = 0.01 * (i % 3) * 255
t.color = self.norm_road_color + c
t.road_visited = False
t.road_friction = 1.0
t.idx = i
@@ -385,12 +411,13 @@ class CarRacing(gym.Env, EzPickle):
self.t = 0.0
self.new_lap = False
self.road_poly = []
self._init_colors()
while True:
success = self._create_track()
if success:
break
if self.verbose == 1:
if self.verbose:
print(
"retry to generate track (normal if there are not many"
"instances of this message)"
@@ -402,7 +429,7 @@ class CarRacing(gym.Env, EzPickle):
else:
return self.step(None)[0], {}
def step(self, action):
def step(self, action: np.ndarray):
if action is not None:
self.car.steer(-action[0])
self.car.gas(action[1])
@@ -432,7 +459,7 @@ class CarRacing(gym.Env, EzPickle):
return self.state, step_reward, done, {}
def render(self, mode="human"):
def render(self, mode: str = "human"):
import pygame
pygame.font.init()
@@ -459,13 +486,13 @@ class CarRacing(gym.Env, EzPickle):
trans = pygame.math.Vector2((scroll_x, scroll_y)).rotate_rad(angle)
trans = (WINDOW_W / 2 + trans[0], WINDOW_H / 4 + trans[1])
self.render_road(zoom, trans, angle)
self._render_road(zoom, trans, angle)
self.car.draw(self.surf, zoom, trans, angle, mode != "state_pixels")
self.surf = pygame.transform.flip(self.surf, False, True)
# showing stats
self.render_indicators(WINDOW_W, WINDOW_H)
self._render_indicators(WINDOW_W, WINDOW_H)
font = pygame.font.Font(pygame.font.get_default_font(), 42)
text = font.render("%04i" % self.reward, True, (255, 255, 255), (0, 0, 0))
@@ -487,7 +514,7 @@ class CarRacing(gym.Env, EzPickle):
else:
return self.isopen
def render_road(self, zoom, translation, angle):
def _render_road(self, zoom, translation, angle):
bounds = PLAYFIELD
field = [
(2 * bounds, 2 * bounds),
@@ -495,11 +522,13 @@ class CarRacing(gym.Env, EzPickle):
(0, 0),
(0, 2 * bounds),
]
trans_field = []
self.draw_colored_polygon(
self.surf, field, (102, 204, 102), zoom, translation, angle
# draw background
self._draw_colored_polygon(
self.surf, field, self.bg_color, zoom, translation, angle
)
# draw grass patches
k = bounds / (20.0)
grass = []
for x in range(0, 40, 2):
@@ -513,17 +542,18 @@ class CarRacing(gym.Env, EzPickle):
]
)
for poly in grass:
self.draw_colored_polygon(
self.surf, poly, (102, 230, 102), zoom, translation, angle
self._draw_colored_polygon(
self.surf, poly, self.grass_color, zoom, translation, angle
)
# draw road
for poly, color in self.road_poly:
# converting to pixel coordinates
poly = [(p[0] + PLAYFIELD, p[1] + PLAYFIELD) for p in poly]
color = [int(c * 255) for c in color]
self.draw_colored_polygon(self.surf, poly, color, zoom, translation, angle)
color = [int(c) for c in color]
self._draw_colored_polygon(self.surf, poly, color, zoom, translation, angle)
def render_indicators(self, W, H):
def _render_indicators(self, W, H):
import pygame
s = W / 40.0
@@ -592,7 +622,7 @@ class CarRacing(gym.Env, EzPickle):
(255, 0, 0),
)
def draw_colored_polygon(self, surface, poly, color, zoom, translation, angle):
def _draw_colored_polygon(self, surface, poly, color, zoom, translation, angle):
import pygame
from pygame import gfxdraw

2
gym/envs/registration.py
View File

@@ -649,7 +649,7 @@ def make(id: Literal["LunarLander-v2", "LunarLanderContinuous-v2"], **kwargs) ->
@overload
def make(id: Literal["BipedalWalker-v3", "BipedalWalkerHardcore-v3"], **kwargs) -> Env[np.ndarray, np.ndarray | Sequence[SupportsFloat]]: ...
@overload
def make(id: Literal["CarRacing-v0"], **kwargs) -> Env[np.ndarray, np.ndarray | Sequence[SupportsFloat]]: ...
def make(id: Literal["CarRacing-v1", "CarRacingDomainRandomize-v1"], **kwargs) -> Env[np.ndarray, np.ndarray | Sequence[SupportsFloat]]: ...
# Toy Text
# ----------------------------------------