Bugfixes for continuous case

ml-agents/mlagents/trainers/ppo/optimizer_torch.py

         loss = (
             policy_loss
             + 0.5 * value_loss
-            - decay_bet * ModelUtils.masked_mean(entropy.flatten(), loss_masks)
+            - decay_bet * ModelUtils.masked_mean(entropy, loss_masks)
         )
 
         # Set optimizer learning rate

ml-agents/mlagents/trainers/sac/optimizer_torch.py

             memories = None
             next_memories = None
         # Q network memories are 0'ed out, since we don't have them during inference.
-        q_memories = torch.zeros_like(next_memories)
+        q_memories = (
+            torch.zeros_like(next_memories) if next_memories is not None else None
+        )
 
         vis_obs: List[torch.Tensor] = []
         next_vis_obs: List[torch.Tensor] = []

ml-agents/mlagents/trainers/tests/torch/test_utils.py

     masks = torch.tensor([False, False, False, False, False])
     mean = ModelUtils.masked_mean(test_input, masks=masks)
     assert mean == 0.0
+
+    # Make sure it works with 2d arrays of shape (mask_length, N)
+    test_input = torch.tensor([1, 2, 3, 4, 5]).repeat(2, 1).T
+    masks = torch.tensor([False, False, True, True, True])
+    mean = ModelUtils.masked_mean(test_input, masks=masks)
+    assert mean == 4.0

ml-agents/mlagents/trainers/torch/utils.py

         :param tensor: Tensor which needs mean computation.
         :param masks: Boolean tensor of masks with same dimension as tensor.
         """
-        return (tensor * masks).sum() / torch.clamp(masks.float().sum(), min=1.0)
+        return (tensor.T * masks).sum() / torch.clamp(
+            (torch.ones_like(tensor.T) * masks).float().sum(), min=1.0
+        )