obstructedmaze.py 6.7 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211
  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. ):
  15. room_size = 6
  16. max_steps = 4*num_rooms_visited*room_size**2
  17. super().__init__(
  18. room_size=room_size,
  19. num_rows=num_rows,
  20. num_cols=num_cols,
  21. max_steps=max_steps,
  22. seed=seed
  23. )
  24. def _gen_grid(self, width, height):
  25. super()._gen_grid(width, height)
  26. # Define all possible colors for doors
  27. self.door_colors = self._rand_subset(COLOR_NAMES, len(COLOR_NAMES))
  28. # Define the color of the ball to pick up
  29. self.ball_to_find_color = COLOR_NAMES[0]
  30. # Define the color of the balls that obstruct doors
  31. self.blocking_ball_color = COLOR_NAMES[1]
  32. # Define the color of boxes in which keys are hidden
  33. self.box_color = COLOR_NAMES[2]
  34. self.mission = "pick up the %s ball" % self.ball_to_find_color
  35. def step(self, action):
  36. obs, reward, done, info = super().step(action)
  37. if action == self.actions.pickup:
  38. if self.carrying and self.carrying == self.obj:
  39. reward = self._reward()
  40. done = True
  41. return obs, reward, done, info
  42. def add_door(self, i, j, door_idx=0, color=None, locked=False, key_in_box=False, blocked=False):
  43. """
  44. Add a door. If the door must be locked, it also adds the key.
  45. If the key must be hidden, it is put in a box. If the door must
  46. be obstructed, it adds a ball in front of the door.
  47. """
  48. door, door_pos = super().add_door(i, j, door_idx, color, locked=locked)
  49. if blocked:
  50. vec = DIR_TO_VEC[door_idx]
  51. blocking_ball = Ball(self.blocking_ball_color) if blocked else None
  52. self.grid.set(door_pos[0]-vec[0], door_pos[1]-vec[1], blocking_ball)
  53. if locked:
  54. obj = Key(door.color)
  55. if key_in_box:
  56. box = Box(self.box_color) if key_in_box else None
  57. box.contains = obj
  58. obj = box
  59. self.place_in_room(i, j, obj)
  60. return door, door_pos
  61. class ObstructedMaze_1Dlhb(ObstructedMazeEnv):
  62. """
  63. A blue ball is hidden in a 2x1 maze. A locked door separates
  64. rooms. Doors are obstructed by a ball and keys are hidden in boxes.
  65. """
  66. def __init__(self, key_in_box=True, blocked=True, seed=None):
  67. self.key_in_box = key_in_box
  68. self.blocked = blocked
  69. super().__init__(
  70. num_rows=1,
  71. num_cols=2,
  72. num_rooms_visited=2,
  73. seed=seed
  74. )
  75. def _gen_grid(self, width, height):
  76. super()._gen_grid(width, height)
  77. self.add_door(0, 0, door_idx=0, color=self.door_colors[0],
  78. locked=True,
  79. key_in_box=self.key_in_box,
  80. blocked=self.blocked)
  81. self.obj, _ = self.add_object(1, 0, "ball", color=self.ball_to_find_color)
  82. self.place_agent(0, 0)
  83. class ObstructedMaze_Full(ObstructedMazeEnv):
  84. """
  85. A blue ball is hidden in one of the 4 corners of a 3x3 maze. Doors
  86. are locked, doors are obstructed by a ball and keys are hidden in
  87. boxes.
  88. """
  89. def __init__(self, agent_room=(1, 1), key_in_box=True, blocked=True,
  90. num_quarters=4, num_rooms_visited=25, seed=None):
  91. self.agent_room = agent_room
  92. self.key_in_box = key_in_box
  93. self.blocked = blocked
  94. self.num_quarters = num_quarters
  95. super().__init__(
  96. num_rows=3,
  97. num_cols=3,
  98. num_rooms_visited=num_rooms_visited,
  99. seed=seed
  100. )
  101. def _gen_grid(self, width, height):
  102. super()._gen_grid(width, height)
  103. middle_room = (1, 1)
  104. # Define positions of "side rooms" i.e. rooms that are neither
  105. # corners nor the center.
  106. side_rooms = [(2, 1), (1, 2), (0, 1), (1, 0)][:self.num_quarters]
  107. for i in range(len(side_rooms)):
  108. side_room = side_rooms[i]
  109. # Add a door between the center room and the side room
  110. self.add_door(*middle_room, door_idx=i, color=self.door_colors[i], locked=False)
  111. for k in [-1, 1]:
  112. # Add a door to each side of the side room
  113. self.add_door(*side_room, locked=True,
  114. door_idx=(i+k)%4,
  115. color=self.door_colors[(i+k)%len(self.door_colors)],
  116. key_in_box=self.key_in_box,
  117. blocked=self.blocked)
  118. corners = [(2, 0), (2, 2), (0, 2), (0, 0)][:self.num_quarters]
  119. ball_room = self._rand_elem(corners)
  120. self.obj, _ = self.add_object(*ball_room, "ball", color=self.ball_to_find_color)
  121. self.place_agent(*self.agent_room)
  122. register(
  123. id="MiniGrid-ObstructedMaze-1Dl-v0",
  124. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_1Dlhb",
  125. key_in_box=False, blocked=False
  126. )
  127. register(
  128. id="MiniGrid-ObstructedMaze-1Dlh-v0",
  129. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_1Dlhb",
  130. key_in_box=True, blocked=False
  131. )
  132. register(
  133. id="MiniGrid-ObstructedMaze-1Dlhb-v0",
  134. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_1Dlhb"
  135. )
  136. register(
  137. id="MiniGrid-ObstructedMaze-2Dl-v0",
  138. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_Full",
  139. agent_room=(2, 1), key_in_box=False, blocked=False,
  140. num_quarters=1, num_rooms_visited=4,
  141. )
  142. register(
  143. id="MiniGrid-ObstructedMaze-2Dlh-v0",
  144. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_Full",
  145. agent_room=(2, 1), key_in_box=True, blocked=False,
  146. num_quarters=1, num_rooms_visited=4,
  147. )
  148. register(
  149. id="MiniGrid-ObstructedMaze-2Dlhb-v0",
  150. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_Full",
  151. agent_room=(2, 1), key_in_box=True, blocked=True,
  152. num_quarters=1, num_rooms_visited=4,
  153. )
  154. register(
  155. id="MiniGrid-ObstructedMaze-1Q-v0",
  156. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_Full",
  157. agent_room=(1, 1), key_in_box=True, blocked=True,
  158. num_quarters=1, num_rooms_visited=5,
  159. )
  160. register(
  161. id="MiniGrid-ObstructedMaze-2Q-v0",
  162. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_Full",
  163. agent_room=(2, 1), key_in_box=True, blocked=True,
  164. num_quarters=2, num_rooms_visited=11,
  165. )
  166. register(
  167. id="MiniGrid-ObstructedMaze-Full-v0",
  168. entry_point="gym_minigrid.envs.obstructedmaze:ObstructedMaze_Full"
  169. )