avoid DeprecationWarning

envs/memorymaze.py

@@ -36,9 +36,9 @@ class MemoryMaze:
         return {
             **spaces,
             "reward": gym.spaces.Box(-np.inf, np.inf, (), dtype=np.float32),
-            "is_first": gym.spaces.Box(0, 1, (), dtype=np.bool),
-            "is_last": gym.spaces.Box(0, 1, (), dtype=np.bool),
-            "is_terminal": gym.spaces.Box(0, 1, (), dtype=np.bool),
+            "is_first": gym.spaces.Box(0, 1, (), dtype=bool),
+            "is_last": gym.spaces.Box(0, 1, (), dtype=bool),
+            "is_terminal": gym.spaces.Box(0, 1, (), dtype=bool),
         }
 
     @property

envs/wrappers.py

@@ -77,8 +77,8 @@ class CollectDataset:
             dtype = {16: np.int16, 32: np.int32, 64: np.int64}[self._precision]
         elif np.issubdtype(value.dtype, np.uint8):
             dtype = np.uint8
-        elif np.issubdtype(value.dtype, np.bool):
-            dtype = np.bool
+        elif np.issubdtype(value.dtype, bool):
+            dtype = bool
         else:
             raise NotImplementedError(value.dtype)
         return value.astype(dtype)

requirements.txt

@@ -9,4 +9,5 @@ moviepy==1.0.3
 einops==0.3.0
 protobuf==3.20.0
 gym==0.19.0
-dm_control==1.0.9
+dm_control==1.0.9
+scipy==scipy==1.9.0

tools.py

@@ -127,7 +127,7 @@ def simulate(agent, envs, steps=0, episodes=0, state=None):
     # Initialize or unpack simulation state.
     if state is None:
         step, episode = 0, 0
-        done = np.ones(len(envs), np.bool)
+        done = np.ones(len(envs), bool)
         length = np.zeros(len(envs), np.int32)
         obs = [None] * len(envs)
         agent_state = None