redbluedoors.py 2.3 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778
  1. from gym_minigrid.minigrid import Door, Grid, MiniGridEnv
  2. from gym_minigrid.register import register
  3. class RedBlueDoorEnv(MiniGridEnv):
  4. """
  5. Single room with red and blue doors on opposite sides.
  6. The red door must be opened before the blue door to
  7. obtain a reward.
  8. """
  9. def __init__(self, size=8, **kwargs):
  10. self.size = size
  11. super().__init__(
  12. width=2 * size, height=size, max_steps=20 * size * size, **kwargs
  13. )
  14. def _gen_grid(self, width, height):
  15. # Create an empty grid
  16. self.grid = Grid(width, height)
  17. # Generate the grid walls
  18. self.grid.wall_rect(0, 0, 2 * self.size, self.size)
  19. self.grid.wall_rect(self.size // 2, 0, self.size, self.size)
  20. # Place the agent in the top-left corner
  21. self.place_agent(top=(self.size // 2, 0), size=(self.size, self.size))
  22. # Add a red door at a random position in the left wall
  23. pos = self._rand_int(1, self.size - 1)
  24. self.red_door = Door("red")
  25. self.grid.set(self.size // 2, pos, self.red_door)
  26. # Add a blue door at a random position in the right wall
  27. pos = self._rand_int(1, self.size - 1)
  28. self.blue_door = Door("blue")
  29. self.grid.set(self.size // 2 + self.size - 1, pos, self.blue_door)
  30. # Generate the mission string
  31. self.mission = "open the red door then the blue door"
  32. def step(self, action):
  33. red_door_opened_before = self.red_door.is_open
  34. blue_door_opened_before = self.blue_door.is_open
  35. obs, reward, done, info = MiniGridEnv.step(self, action)
  36. red_door_opened_after = self.red_door.is_open
  37. blue_door_opened_after = self.blue_door.is_open
  38. if blue_door_opened_after:
  39. if red_door_opened_before:
  40. reward = self._reward()
  41. done = True
  42. else:
  43. reward = 0
  44. done = True
  45. elif red_door_opened_after:
  46. if blue_door_opened_before:
  47. reward = 0
  48. done = True
  49. return obs, reward, done, info
  50. register(
  51. id="MiniGrid-RedBlueDoors-6x6-v0",
  52. entry_point="gym_minigrid.envs.redbluedoors:RedBlueDoorEnv",
  53. size=6,
  54. )
  55. register(
  56. id="MiniGrid-RedBlueDoors-8x8-v0",
  57. entry_point="gym_minigrid.envs.redbluedoors:RedBlueDoorEnv",
  58. )