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):
  10. self.size = size
  11. super().__init__(width=2 * size, height=size, max_steps=20 * size * size)
  12. def _gen_grid(self, width, height):
  13. # Create an empty grid
  14. self.grid = Grid(width, height)
  15. # Generate the grid walls
  16. self.grid.wall_rect(0, 0, 2 * self.size, self.size)
  17. self.grid.wall_rect(self.size // 2, 0, self.size, self.size)
  18. # Place the agent in the top-left corner
  19. self.place_agent(top=(self.size // 2, 0), size=(self.size, self.size))
  20. # Add a red door at a random position in the left wall
  21. pos = self._rand_int(1, self.size - 1)
  22. self.red_door = Door("red")
  23. self.grid.set(self.size // 2, pos, self.red_door)
  24. # Add a blue door at a random position in the right wall
  25. pos = self._rand_int(1, self.size - 1)
  26. self.blue_door = Door("blue")
  27. self.grid.set(self.size // 2 + self.size - 1, pos, self.blue_door)
  28. # Generate the mission string
  29. self.mission = "open the red door then the blue door"
  30. def step(self, action):
  31. red_door_opened_before = self.red_door.is_open
  32. blue_door_opened_before = self.blue_door.is_open
  33. obs, reward, done, info = MiniGridEnv.step(self, action)
  34. red_door_opened_after = self.red_door.is_open
  35. blue_door_opened_after = self.blue_door.is_open
  36. if blue_door_opened_after:
  37. if red_door_opened_before:
  38. reward = self._reward()
  39. done = True
  40. else:
  41. reward = 0
  42. done = True
  43. elif red_door_opened_after:
  44. if blue_door_opened_before:
  45. reward = 0
  46. done = True
  47. return obs, reward, done, info
  48. class RedBlueDoorEnv6x6(RedBlueDoorEnv):
  49. def __init__(self):
  50. super().__init__(size=6)
  51. register(
  52. id="MiniGrid-RedBlueDoors-6x6-v0", entry_point="gym_minigrid.envs:RedBlueDoorEnv6x6"
  53. )
  54. register(
  55. id="MiniGrid-RedBlueDoors-8x8-v0", entry_point="gym_minigrid.envs:RedBlueDoorEnv"
  56. )