redbluedoors.py 2.4 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182
  1. from gym_minigrid.minigrid import *
  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,
  13. height=size,
  14. max_steps=20*size*size,
  15. **kwargs
  16. )
  17. def _gen_grid(self, width, height):
  18. # Create an empty grid
  19. self.grid = Grid(width, height)
  20. # Generate the grid walls
  21. self.grid.wall_rect(0, 0, 2*self.size, self.size)
  22. self.grid.wall_rect(self.size//2, 0, self.size, self.size)
  23. # Place the agent in the top-left corner
  24. self.place_agent(top=(self.size//2, 0), size=(self.size, self.size))
  25. # Add a red door at a random position in the left wall
  26. pos = self._rand_int(1, self.size - 1)
  27. self.red_door = Door("red")
  28. self.grid.set(self.size//2, pos, self.red_door)
  29. # Add a blue door at a random position in the right wall
  30. pos = self._rand_int(1, self.size - 1)
  31. self.blue_door = Door("blue")
  32. self.grid.set(self.size//2 + self.size - 1, pos, self.blue_door)
  33. # Generate the mission string
  34. self.mission = "open the red door then the blue door"
  35. def step(self, action):
  36. red_door_opened_before = self.red_door.is_open
  37. blue_door_opened_before = self.blue_door.is_open
  38. obs, reward, done, info = MiniGridEnv.step(self, action)
  39. red_door_opened_after = self.red_door.is_open
  40. blue_door_opened_after = self.blue_door.is_open
  41. if blue_door_opened_after:
  42. if red_door_opened_before:
  43. reward = self._reward()
  44. done = True
  45. else:
  46. reward = 0
  47. done = True
  48. elif red_door_opened_after:
  49. if blue_door_opened_before:
  50. reward = 0
  51. done = True
  52. return obs, reward, done, info
  53. class RedBlueDoorEnv6x6(RedBlueDoorEnv):
  54. def __init__(self, **kwargs):
  55. super().__init__(size=6, **kwargs)
  56. register(
  57. id='MiniGrid-RedBlueDoors-6x6-v0',
  58. entry_point='gym_minigrid.envs:RedBlueDoorEnv6x6'
  59. )
  60. register(
  61. id='MiniGrid-RedBlueDoors-8x8-v0',
  62. entry_point='gym_minigrid.envs:RedBlueDoorEnv'
  63. )