obstructedmaze.py 8.5 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259
  1. from minigrid.core.constants import COLOR_NAMES, DIR_TO_VEC
  2. from minigrid.core.mission import MissionSpace
  3. from minigrid.core.roomgrid import RoomGrid
  4. from minigrid.core.world_object import Ball, Box, Key
  5. class ObstructedMazeEnv(RoomGrid):
  6. """
  7. ![ObstructedMaze-1Dl](../_static/figures/ObstructedMaze-1Dl.png)<br />
  8. ![ObstructedMaze-1Dlh](../_static/figures/ObstructedMaze-1Dlh.png)<br />
  9. ![ObstructedMaze-1Dlhb](../_static/figures/ObstructedMaze-1Dlhb.png)<br />
  10. ![ObstructedMaze-1Q](../_static/figures/ObstructedMaze-1Q.png)<br />
  11. ![ObstructedMaze-2Dl](../_static/figures/ObstructedMaze-2Dl.png)<br />
  12. ![ObstructedMaze-2Dlh](../_static/figures/ObstructedMaze-2Dlh.png)<br />
  13. ![ObstructedMaze-2Dlhb](../_static/figures/ObstructedMaze-2Dlhb.png)<br />
  14. ![ObstructedMaze-2Q](../_static/figures/ObstructedMaze-2Q.png)<br />
  15. ![ObstructedMaze-4Q](../_static/figures/ObstructedMaze-4Q.png)<br />
  16. ### Description
  17. The agent has to pick up a box which is placed in a corner of a 3x3 maze.
  18. The doors are locked, the keys are hidden in boxes and doors are obstructed
  19. by balls. This environment can be solved without relying on language.
  20. ### Mission Space
  21. "pick up the {COLOR_NAMES[0]} ball"
  22. ### Action Space
  23. | Num | Name | Action |
  24. |-----|--------------|---------------------------|
  25. | 0 | left | Turn left |
  26. | 1 | right | Turn right |
  27. | 2 | forward | Move forward |
  28. | 3 | pickup | Pick up an object |
  29. | 4 | drop | Unused |
  30. | 5 | toggle | Toggle/activate an object |
  31. | 6 | done | Unused |
  32. ### Observation Encoding
  33. - Each tile is encoded as a 3 dimensional tuple:
  34. `(OBJECT_IDX, COLOR_IDX, STATE)`
  35. - `OBJECT_TO_IDX` and `COLOR_TO_IDX` mapping can be found in
  36. [minigrid/minigrid.py](minigrid/minigrid.py)
  37. - `STATE` refers to the door state with 0=open, 1=closed and 2=locked
  38. ### Rewards
  39. A reward of '1' is given for success, and '0' for failure.
  40. ### Termination
  41. The episode ends if any one of the following conditions is met:
  42. 1. The agent picks up the blue ball.
  43. 2. Timeout (see `max_steps`).
  44. ### Registered Configurations
  45. "NDl" are the number of doors locked.
  46. "h" if the key is hidden in a box.
  47. "b" if the door is obstructed by a ball.
  48. "Q" number of quarters that will have doors and keys out of the 9 that the
  49. map already has.
  50. "Full" 3x3 maze with "h" and "b" options.
  51. - `MiniGrid-ObstructedMaze-1Dl-v0`
  52. - `MiniGrid-ObstructedMaze-1Dlh-v0`
  53. - `MiniGrid-ObstructedMaze-1Dlhb-v0`
  54. - `MiniGrid-ObstructedMaze-2Dl-v0`
  55. - `MiniGrid-ObstructedMaze-2Dlh-v0`
  56. - `MiniGrid-ObstructedMaze-2Dlhb-v0`
  57. - `MiniGrid-ObstructedMaze-1Q-v0`
  58. - `MiniGrid-ObstructedMaze-2Q-v0`
  59. - `MiniGrid-ObstructedMaze-Full-v0`
  60. """
  61. def __init__(self, num_rows, num_cols, num_rooms_visited, **kwargs):
  62. room_size = 6
  63. max_steps = 4 * num_rooms_visited * room_size**2
  64. mission_space = MissionSpace(
  65. mission_func=lambda: f"pick up the {COLOR_NAMES[0]} ball",
  66. )
  67. super().__init__(
  68. mission_space=mission_space,
  69. room_size=room_size,
  70. num_rows=num_rows,
  71. num_cols=num_cols,
  72. max_steps=max_steps,
  73. **kwargs,
  74. )
  75. self.obj = Ball() # initialize the obj attribute, that will be changed later on
  76. def _gen_grid(self, width, height):
  77. super()._gen_grid(width, height)
  78. # Define all possible colors for doors
  79. self.door_colors = self._rand_subset(COLOR_NAMES, len(COLOR_NAMES))
  80. # Define the color of the ball to pick up
  81. self.ball_to_find_color = COLOR_NAMES[0]
  82. # Define the color of the balls that obstruct doors
  83. self.blocking_ball_color = COLOR_NAMES[1]
  84. # Define the color of boxes in which keys are hidden
  85. self.box_color = COLOR_NAMES[2]
  86. self.mission = "pick up the %s ball" % self.ball_to_find_color
  87. def step(self, action):
  88. obs, reward, terminated, truncated, info = super().step(action)
  89. if action == self.actions.pickup:
  90. if self.carrying and self.carrying == self.obj:
  91. reward = self._reward()
  92. terminated = True
  93. return obs, reward, terminated, truncated, info
  94. def add_door(
  95. self,
  96. i,
  97. j,
  98. door_idx=0,
  99. color=None,
  100. locked=False,
  101. key_in_box=False,
  102. blocked=False,
  103. ):
  104. """
  105. Add a door. If the door must be locked, it also adds the key.
  106. If the key must be hidden, it is put in a box. If the door must
  107. be obstructed, it adds a ball in front of the door.
  108. """
  109. door, door_pos = super().add_door(i, j, door_idx, color, locked=locked)
  110. if blocked:
  111. vec = DIR_TO_VEC[door_idx]
  112. blocking_ball = Ball(self.blocking_ball_color) if blocked else None
  113. self.grid.set(door_pos[0] - vec[0], door_pos[1] - vec[1], blocking_ball)
  114. if locked:
  115. obj = Key(door.color)
  116. if key_in_box:
  117. box = Box(self.box_color)
  118. box.contains = obj
  119. obj = box
  120. self.place_in_room(i, j, obj)
  121. return door, door_pos
  122. class ObstructedMaze_1Dlhb(ObstructedMazeEnv):
  123. """
  124. A blue ball is hidden in a 2x1 maze. A locked door separates
  125. rooms. Doors are obstructed by a ball and keys are hidden in boxes.
  126. """
  127. def __init__(self, key_in_box=True, blocked=True, **kwargs):
  128. self.key_in_box = key_in_box
  129. self.blocked = blocked
  130. super().__init__(num_rows=1, num_cols=2, num_rooms_visited=2, **kwargs)
  131. def _gen_grid(self, width, height):
  132. super()._gen_grid(width, height)
  133. self.add_door(
  134. 0,
  135. 0,
  136. door_idx=0,
  137. color=self.door_colors[0],
  138. locked=True,
  139. key_in_box=self.key_in_box,
  140. blocked=self.blocked,
  141. )
  142. self.obj, _ = self.add_object(1, 0, "ball", color=self.ball_to_find_color)
  143. self.place_agent(0, 0)
  144. class ObstructedMaze_Full(ObstructedMazeEnv):
  145. """
  146. A blue ball is hidden in one of the 4 corners of a 3x3 maze. Doors
  147. are locked, doors are obstructed by a ball and keys are hidden in
  148. boxes.
  149. """
  150. def __init__(
  151. self,
  152. agent_room=(1, 1),
  153. key_in_box=True,
  154. blocked=True,
  155. num_quarters=4,
  156. num_rooms_visited=25,
  157. **kwargs,
  158. ):
  159. self.agent_room = agent_room
  160. self.key_in_box = key_in_box
  161. self.blocked = blocked
  162. self.num_quarters = num_quarters
  163. super().__init__(
  164. num_rows=3, num_cols=3, num_rooms_visited=num_rooms_visited, **kwargs
  165. )
  166. def _gen_grid(self, width, height):
  167. super()._gen_grid(width, height)
  168. middle_room = (1, 1)
  169. # Define positions of "side rooms" i.e. rooms that are neither
  170. # corners nor the center.
  171. side_rooms = [(2, 1), (1, 2), (0, 1), (1, 0)][: self.num_quarters]
  172. for i in range(len(side_rooms)):
  173. side_room = side_rooms[i]
  174. # Add a door between the center room and the side room
  175. self.add_door(
  176. *middle_room, door_idx=i, color=self.door_colors[i], locked=False
  177. )
  178. for k in [-1, 1]:
  179. # Add a door to each side of the side room
  180. self.add_door(
  181. *side_room,
  182. locked=True,
  183. door_idx=(i + k) % 4,
  184. color=self.door_colors[(i + k) % len(self.door_colors)],
  185. key_in_box=self.key_in_box,
  186. blocked=self.blocked,
  187. )
  188. corners = [(2, 0), (2, 2), (0, 2), (0, 0)][: self.num_quarters]
  189. ball_room = self._rand_elem(corners)
  190. self.obj, _ = self.add_object(
  191. ball_room[0], ball_room[1], "ball", color=self.ball_to_find_color
  192. )
  193. self.place_agent(*self.agent_room)
  194. class ObstructedMaze_2Dl(ObstructedMaze_Full):
  195. def __init__(self, **kwargs):
  196. super().__init__((2, 1), False, False, 1, 4, **kwargs)
  197. class ObstructedMaze_2Dlh(ObstructedMaze_Full):
  198. def __init__(self, **kwargs):
  199. super().__init__((2, 1), True, False, 1, 4, **kwargs)
  200. class ObstructedMaze_2Dlhb(ObstructedMaze_Full):
  201. def __init__(self, **kwargs):
  202. super().__init__((2, 1), True, True, 1, 4, **kwargs)