redbluedoors.py 2.3 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879
  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. width=2*size,
  11. height=size,
  12. max_steps=10*size*size
  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. class RedBlueDoorEnv6x6(RedBlueDoorEnv):
  51. def __init__(self):
  52. super().__init__(size=6)
  53. register(
  54. id='MiniGrid-RedBlueDoors-6x6-v0',
  55. entry_point='gym_minigrid.envs:RedBlueDoorEnv6x6'
  56. )
  57. register(
  58. id='MiniGrid-RedBlueDoors-8x8-v0',
  59. entry_point='gym_minigrid.envs:RedBlueDoorEnv'
  60. )