obstructedmaze.py 7.2 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228
  1. from gym_minigrid.minigrid import *
  2. from gym_minigrid.roomgrid import RoomGrid
  3. from gym_minigrid.register import register
  4. class ObstructedMazeEnv(RoomGrid):
  5. """
  6. A blue ball is hidden in the maze. Doors may be locked,
  7. doors may be obstructed by a ball and keys may be hidden in boxes.
  8. """
  9. def __init__(self,
  10. num_rows,
  11. num_cols,
  12. num_rooms_visited,
  13. seed=None,
  14. **kwargs
  15. ):
  16. room_size = 6
  17. max_steps = 4*num_rooms_visited*room_size**2
  18. super().__init__(
  19. room_size=room_size,
  20. num_rows=num_rows,
  21. num_cols=num_cols,
  22. max_steps=max_steps,
  23. seed=seed,
  24. **kwargs
  25. )
  26. def _gen_grid(self, width, height):
  27. super()._gen_grid(width, height)
  28. # Define all possible colors for doors
  29. self.door_colors = self._rand_subset(COLOR_NAMES, len(COLOR_NAMES))
  30. # Define the color of the ball to pick up
  31. self.ball_to_find_color = COLOR_NAMES[0]
  32. # Define the color of the balls that obstruct doors
  33. self.blocking_ball_color = COLOR_NAMES[1]
  34. # Define the color of boxes in which keys are hidden
  35. self.box_color = COLOR_NAMES[2]
  36. self.mission = "pick up the %s ball" % self.ball_to_find_color
  37. def step(self, action):
  38. obs, reward, done, info = super().step(action)
  39. if action == self.actions.pickup:
  40. if self.carrying and self.carrying == self.obj:
  41. reward = self._reward()
  42. done = True
  43. return obs, reward, done, info
  44. def add_door(self, i, j, door_idx=0, color=None, locked=False, key_in_box=False, blocked=False):
  45. """
  46. Add a door. If the door must be locked, it also adds the key.
  47. If the key must be hidden, it is put in a box. If the door must
  48. be obstructed, it adds a ball in front of the door.
  49. """
  50. door, door_pos = super().add_door(i, j, door_idx, color, locked=locked)
  51. if blocked:
  52. vec = DIR_TO_VEC[door_idx]
  53. blocking_ball = Ball(self.blocking_ball_color) if blocked else None
  54. self.grid.set(door_pos[0]-vec[0], door_pos[1]-vec[1], blocking_ball)
  55. if locked:
  56. obj = Key(door.color)
  57. if key_in_box:
  58. box = Box(self.box_color) if key_in_box else None
  59. box.contains = obj
  60. obj = box
  61. self.place_in_room(i, j, obj)
  62. return door, door_pos
  63. class ObstructedMaze_1Dlhb(ObstructedMazeEnv):
  64. """
  65. A blue ball is hidden in a 2x1 maze. A locked door separates
  66. rooms. Doors are obstructed by a ball and keys are hidden in boxes.
  67. """
  68. def __init__(self, key_in_box=True, blocked=True, seed=None, **kwargs):
  69. self.key_in_box = key_in_box
  70. self.blocked = blocked
  71. super().__init__(
  72. num_rows=1,
  73. num_cols=2,
  74. num_rooms_visited=2,
  75. seed=seed,
  76. **kwargs
  77. )
  78. def _gen_grid(self, width, height):
  79. super()._gen_grid(width, height)
  80. self.add_door(0, 0, door_idx=0, color=self.door_colors[0],
  81. locked=True,
  82. key_in_box=self.key_in_box,
  83. blocked=self.blocked)
  84. self.obj, _ = self.add_object(1, 0, "ball", color=self.ball_to_find_color)
  85. self.place_agent(0, 0)
  86. class ObstructedMaze_1Dl(ObstructedMaze_1Dlhb):
  87. def __init__(self, seed=None, **kwargs):
  88. super().__init__(False, False, seed, **kwargs)
  89. class ObstructedMaze_1Dlh(ObstructedMaze_1Dlhb):
  90. def __init__(self, seed=None, **kwargs):
  91. super().__init__(True, False, seed, **kwargs)
  92. class ObstructedMaze_Full(ObstructedMazeEnv):
  93. """
  94. A blue ball is hidden in one of the 4 corners of a 3x3 maze. Doors
  95. are locked, doors are obstructed by a ball and keys are hidden in
  96. boxes.
  97. """
  98. def __init__(self, agent_room=(1, 1), key_in_box=True, blocked=True,
  99. num_quarters=4, num_rooms_visited=25, seed=None, **kwargs):
  100. self.agent_room = agent_room
  101. self.key_in_box = key_in_box
  102. self.blocked = blocked
  103. self.num_quarters = num_quarters
  104. super().__init__(
  105. num_rows=3,
  106. num_cols=3,
  107. num_rooms_visited=num_rooms_visited,
  108. seed=seed,
  109. **kwargs
  110. )
  111. def _gen_grid(self, width, height):
  112. super()._gen_grid(width, height)
  113. middle_room = (1, 1)
  114. # Define positions of "side rooms" i.e. rooms that are neither
  115. # corners nor the center.
  116. side_rooms = [(2, 1), (1, 2), (0, 1), (1, 0)][:self.num_quarters]
  117. for i in range(len(side_rooms)):
  118. side_room = side_rooms[i]
  119. # Add a door between the center room and the side room
  120. self.add_door(*middle_room, door_idx=i, color=self.door_colors[i], locked=False)
  121. for k in [-1, 1]:
  122. # Add a door to each side of the side room
  123. self.add_door(*side_room, locked=True,
  124. door_idx=(i+k)%4,
  125. color=self.door_colors[(i+k)%len(self.door_colors)],
  126. key_in_box=self.key_in_box,
  127. blocked=self.blocked)
  128. corners = [(2, 0), (2, 2), (0, 2), (0, 0)][:self.num_quarters]
  129. ball_room = self._rand_elem(corners)
  130. self.obj, _ = self.add_object(*ball_room, "ball", color=self.ball_to_find_color)
  131. self.place_agent(*self.agent_room)
  132. class ObstructedMaze_2Dl(ObstructedMaze_Full):
  133. def __init__(self, seed=None, **kwargs):
  134. super().__init__((2, 1), False, False, 1, 4, seed, **kwargs)
  135. class ObstructedMaze_2Dlh(ObstructedMaze_Full):
  136. def __init__(self, seed=None, **kwargs):
  137. super().__init__((2, 1), True, False, 1, 4, seed, **kwargs)
  138. class ObstructedMaze_2Dlhb(ObstructedMaze_Full):
  139. def __init__(self, seed=None, **kwargs):
  140. super().__init__((2, 1), True, True, 1, 4, seed, **kwargs)
  141. class ObstructedMaze_1Q(ObstructedMaze_Full):
  142. def __init__(self, seed=None, **kwargs):
  143. super().__init__((1, 1), True, True, 1, 5, seed, **kwargs)
  144. class ObstructedMaze_2Q(ObstructedMaze_Full):
  145. def __init__(self, seed=None, **kwargs):
  146. super().__init__((1, 1), True, True, 2, 11, seed, **kwargs)
  147. register(
  148. id="MiniGrid-ObstructedMaze-1Dl-v0",
  149. entry_point="gym_minigrid.envs:ObstructedMaze_1Dl"
  150. )
  151. register(
  152. id="MiniGrid-ObstructedMaze-1Dlh-v0",
  153. entry_point="gym_minigrid.envs:ObstructedMaze_1Dlh"
  154. )
  155. register(
  156. id="MiniGrid-ObstructedMaze-1Dlhb-v0",
  157. entry_point="gym_minigrid.envs:ObstructedMaze_1Dlhb"
  158. )
  159. register(
  160. id="MiniGrid-ObstructedMaze-2Dl-v0",
  161. entry_point="gym_minigrid.envs:ObstructedMaze_2Dl"
  162. )
  163. register(
  164. id="MiniGrid-ObstructedMaze-2Dlh-v0",
  165. entry_point="gym_minigrid.envs:ObstructedMaze_2Dlh"
  166. )
  167. register(
  168. id="MiniGrid-ObstructedMaze-2Dlhb-v0",
  169. entry_point="gym_minigrid.envs:ObstructedMaze_2Dlhb"
  170. )
  171. register(
  172. id="MiniGrid-ObstructedMaze-1Q-v0",
  173. entry_point="gym_minigrid.envs:ObstructedMaze_1Q"
  174. )
  175. register(
  176. id="MiniGrid-ObstructedMaze-2Q-v0",
  177. entry_point="gym_minigrid.envs:ObstructedMaze_2Q"
  178. )
  179. register(
  180. id="MiniGrid-ObstructedMaze-Full-v0",
  181. entry_point="gym_minigrid.envs:ObstructedMaze_Full"
  182. )