obstructedmaze.py 5.5 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181
  1. from gym_minigrid.minigrid import COLOR_NAMES, DIR_TO_VEC, Ball, Box, Key
  2. from gym_minigrid.roomgrid import RoomGrid
  3. class ObstructedMazeEnv(RoomGrid):
  4. """
  5. A blue ball is hidden in the maze. Doors may be locked,
  6. doors may be obstructed by a ball and keys may be hidden in boxes.
  7. """
  8. def __init__(self, num_rows, num_cols, num_rooms_visited, **kwargs):
  9. room_size = 6
  10. max_steps = 4 * num_rooms_visited * room_size**2
  11. super().__init__(
  12. room_size=room_size,
  13. num_rows=num_rows,
  14. num_cols=num_cols,
  15. max_steps=max_steps,
  16. **kwargs
  17. )
  18. def _gen_grid(self, width, height):
  19. super()._gen_grid(width, height)
  20. # Define all possible colors for doors
  21. self.door_colors = self._rand_subset(COLOR_NAMES, len(COLOR_NAMES))
  22. # Define the color of the ball to pick up
  23. self.ball_to_find_color = COLOR_NAMES[0]
  24. # Define the color of the balls that obstruct doors
  25. self.blocking_ball_color = COLOR_NAMES[1]
  26. # Define the color of boxes in which keys are hidden
  27. self.box_color = COLOR_NAMES[2]
  28. self.mission = "pick up the %s ball" % self.ball_to_find_color
  29. def step(self, action):
  30. obs, reward, done, info = super().step(action)
  31. if action == self.actions.pickup:
  32. if self.carrying and self.carrying == self.obj:
  33. reward = self._reward()
  34. done = True
  35. return obs, reward, done, info
  36. def add_door(
  37. self,
  38. i,
  39. j,
  40. door_idx=0,
  41. color=None,
  42. locked=False,
  43. key_in_box=False,
  44. blocked=False,
  45. ):
  46. """
  47. Add a door. If the door must be locked, it also adds the key.
  48. If the key must be hidden, it is put in a box. If the door must
  49. be obstructed, it adds a ball in front of the door.
  50. """
  51. door, door_pos = super().add_door(i, j, door_idx, color, locked=locked)
  52. if blocked:
  53. vec = DIR_TO_VEC[door_idx]
  54. blocking_ball = Ball(self.blocking_ball_color) if blocked else None
  55. self.grid.set(door_pos[0] - vec[0], door_pos[1] - vec[1], blocking_ball)
  56. if locked:
  57. obj = Key(door.color)
  58. if key_in_box:
  59. box = Box(self.box_color)
  60. box.contains = obj
  61. obj = box
  62. self.place_in_room(i, j, obj)
  63. return door, door_pos
  64. class ObstructedMaze_1Dlhb(ObstructedMazeEnv):
  65. """
  66. A blue ball is hidden in a 2x1 maze. A locked door separates
  67. rooms. Doors are obstructed by a ball and keys are hidden in boxes.
  68. """
  69. def __init__(self, key_in_box=True, blocked=True, **kwargs):
  70. self.key_in_box = key_in_box
  71. self.blocked = blocked
  72. super().__init__(num_rows=1, num_cols=2, num_rooms_visited=2, **kwargs)
  73. def _gen_grid(self, width, height):
  74. super()._gen_grid(width, height)
  75. self.add_door(
  76. 0,
  77. 0,
  78. door_idx=0,
  79. color=self.door_colors[0],
  80. locked=True,
  81. key_in_box=self.key_in_box,
  82. blocked=self.blocked,
  83. )
  84. self.obj, _ = self.add_object(1, 0, "ball", color=self.ball_to_find_color)
  85. self.place_agent(0, 0)
  86. class ObstructedMaze_Full(ObstructedMazeEnv):
  87. """
  88. A blue ball is hidden in one of the 4 corners of a 3x3 maze. Doors
  89. are locked, doors are obstructed by a ball and keys are hidden in
  90. boxes.
  91. """
  92. def __init__(
  93. self,
  94. agent_room=(1, 1),
  95. key_in_box=True,
  96. blocked=True,
  97. num_quarters=4,
  98. num_rooms_visited=25,
  99. **kwargs
  100. ):
  101. self.agent_room = agent_room
  102. self.key_in_box = key_in_box
  103. self.blocked = blocked
  104. self.num_quarters = num_quarters
  105. super().__init__(
  106. num_rows=3, num_cols=3, num_rooms_visited=num_rooms_visited, **kwargs
  107. )
  108. def _gen_grid(self, width, height):
  109. super()._gen_grid(width, height)
  110. middle_room = (1, 1)
  111. # Define positions of "side rooms" i.e. rooms that are neither
  112. # corners nor the center.
  113. side_rooms = [(2, 1), (1, 2), (0, 1), (1, 0)][: self.num_quarters]
  114. for i in range(len(side_rooms)):
  115. side_room = side_rooms[i]
  116. # Add a door between the center room and the side room
  117. self.add_door(
  118. *middle_room, door_idx=i, color=self.door_colors[i], locked=False
  119. )
  120. for k in [-1, 1]:
  121. # Add a door to each side of the side room
  122. self.add_door(
  123. *side_room,
  124. locked=True,
  125. door_idx=(i + k) % 4,
  126. color=self.door_colors[(i + k) % len(self.door_colors)],
  127. key_in_box=self.key_in_box,
  128. blocked=self.blocked
  129. )
  130. corners = [(2, 0), (2, 2), (0, 2), (0, 0)][: self.num_quarters]
  131. ball_room = self._rand_elem(corners)
  132. self.obj, _ = self.add_object(*ball_room, "ball", color=self.ball_to_find_color)
  133. self.place_agent(*self.agent_room)
  134. class ObstructedMaze_2Dl(ObstructedMaze_Full):
  135. def __init__(self, **kwargs):
  136. super().__init__((2, 1), False, False, 1, 4, **kwargs)
  137. class ObstructedMaze_2Dlh(ObstructedMaze_Full):
  138. def __init__(self, **kwargs):
  139. super().__init__((2, 1), True, False, 1, 4, **kwargs)
  140. class ObstructedMaze_2Dlhb(ObstructedMaze_Full):
  141. def __init__(self, **kwargs):
  142. super().__init__((2, 1), True, True, 1, 4, **kwargs)