redbluedoors.py 2.5 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081
  1. from gym_minigrid.minigrid import *
  2. from gym_minigrid.register import register
  3. class RedBlueDoorEnv(MiniGridEnv):
  4. """
  5. Empty grid environment, no obstacles, sparse reward
  6. """
  7. def __init__(self, size=8):
  8. self.size = size
  9. super().__init__(
  10. grid_size=2*size,
  11. max_steps=20*size*size
  12. )
  13. def _gen_grid(self, width, height):
  14. # Create an empty grid
  15. self.grid = Grid(width, height)
  16. # Generate the grid walls
  17. self.grid.wall_rect(0, 0, 2*self.size, self.size)
  18. self.grid.wall_rect(self.size//2, 0, self.size, self.size)
  19. # Place the agent in the top-left corner
  20. self.start_pos = (self.size, self.size//2)
  21. self.start_dir = 0
  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. # Set the resolution state to 0
  33. # - 0 means "no door opened"
  34. # - 1 means "red door opened"
  35. # - 2 means "red then blue door opened"
  36. self.resolution_state = 0
  37. def step(self, action):
  38. red_door_opened_before = self.red_door.is_open
  39. blue_door_opened_before = self.blue_door.is_open
  40. obs, reward, done, info = MiniGridEnv.step(self, action)
  41. red_door_opened_after = self.red_door.is_open
  42. blue_door_opened_after = self.blue_door.is_open
  43. red_door_opened = red_door_opened_after and not(red_door_opened_before)
  44. blue_door_opened = blue_door_opened_after and not(blue_door_opened_before)
  45. if self.resolution_state == 0 and red_door_opened:
  46. self.resolution_state += 1
  47. elif self.resolution_state == 1 and blue_door_opened:
  48. self.resolution_state += 1
  49. reward = 1
  50. done = True
  51. return obs, reward, done, info
  52. class RedBlueDoorEnv6x6(RedBlueDoorEnv):
  53. def __init__(self):
  54. super().__init__(size=6)
  55. register(
  56. id='MiniGrid-RedBlueDoors-6x6-v0',
  57. entry_point='gym_minigrid.envs:RedBlueDoorEnv6x6'
  58. )
  59. register(
  60. id='MiniGrid-RedBlueDoors-8x8-v0',
  61. entry_point='gym_minigrid.envs:RedBlueDoorEnv'
  62. )