metacontroller-pytorch 0.0.43__py3-none-any.whl → 0.0.46__py3-none-any.whl

metacontroller/metacontroller.py

@@ -54,6 +54,19 @@ def default(*args):
 def straight_through(src, tgt):
     return tgt + src - src.detach()
 
+# losses
+
+BehavioralCloningLosses = namedtuple('BehavioralCloningLosses', (
+    'state',
+    'action'
+))
+
+DiscoveryLosses = namedtuple('DiscoveryLosses', (
+    'action_recon',
+    'kl',
+    'switch'
+))
+
 # meta controller
 
 MetaControllerOutput = namedtuple('MetaControllerOutput', (
@@ -407,10 +420,19 @@ class Transformer(Module):
 
         # meta controller
 
-        self.meta_controller = meta_controller
+        self.meta_controller = meta_controller 
 
         self.register_buffer('zero', tensor(0.), persistent = False)
 
+        # ensure devices match
+        
+        if exists(self.meta_controller): self._ensure_consistent_device(self.meta_controller)
+
+    def _ensure_consistent_device(self, network):
+        self.model_device = next(self.parameters()).device
+        if next(network.parameters()).device != self.model_device:
+            network.to(self.model_device)
+
     def evolve(
         self,
         num_generations,
@@ -441,12 +463,15 @@ class Transformer(Module):
         return_raw_action_dist = False,
         return_latents = False,
         return_cache = False,
-        episode_lens: Tensor | None = None
+        episode_lens: Tensor | None = None,
+        return_meta_controller_output = False
     ):
         device = state.device
 
         # meta controller is either given or already given at init
 
+        if exists(meta_controller): self._ensure_consistent_device(meta_controller)
+
         meta_controller = default(meta_controller, self.meta_controller)
 
         if force_behavior_cloning:
@@ -533,13 +558,23 @@ class Transformer(Module):
 
             action_clone_loss = self.action_readout.calculate_loss(dist_params, target_actions, mask = loss_mask)
 
-            return state_clone_loss, action_clone_loss
+            losses = BehavioralCloningLosses(state_clone_loss, action_clone_loss)
+
+            if not return_meta_controller_output:
+                return losses
+
+            return losses, next_meta_hiddens
 
         elif discovery_phase:
 
             action_recon_loss = self.action_readout.calculate_loss(dist_params, target_actions)
 
-            return action_recon_loss, next_meta_hiddens.kl_loss, next_meta_hiddens.switch_loss
+            losses = DiscoveryLosses(action_recon_loss, next_meta_hiddens.kl_loss, next_meta_hiddens.switch_loss)
+
+            if not return_meta_controller_output:
+                return losses
+
+            return losses, next_meta_hiddens
 
         # returning
 

{metacontroller_pytorch-0.0.43.dist-info → metacontroller_pytorch-0.0.46.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metacontroller-pytorch
-Version: 0.0.43
+Version: 0.0.46
 Summary: Transformer Metacontroller
 Project-URL: Homepage, https://pypi.org/project/metacontroller/
 Project-URL: Repository, https://github.com/lucidrains/metacontroller

{metacontroller_pytorch-0.0.43.dist-info → metacontroller_pytorch-0.0.46.dist-info}/RECORD

@@ -1,8 +1,8 @@
 metacontroller/__init__.py,sha256=iSKbCDp3UrWhZg7SIJFYNjdVQU56u-vqZarE6qCSX74,70
-metacontroller/metacontroller.py,sha256=3L5vPXFm7WbYuuWuCd9RpkMVC--mNpAlsJxpLwMeQ8M,17959
+metacontroller/metacontroller.py,sha256=lp5gd0x59UH7anrzRT8NfmckYJHALqVf8HInYqdgUoQ,18949
 metacontroller/metacontroller_with_binary_mapper.py,sha256=QJG-o4ZuEC6BkYff6nlyhVcze8o1q8GtbtCP8MLPrvc,9927
 metacontroller/transformer_with_resnet.py,sha256=R49ycusbq3kEX97WHZ41WY2ONc2mYPOuRUCmaFcBOEo,5546
-metacontroller_pytorch-0.0.43.dist-info/METADATA,sha256=y1CIKBvy4jTaqsC_FBfiA1FK7pQrqTasiwA96M83luc,6816
-metacontroller_pytorch-0.0.43.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-metacontroller_pytorch-0.0.43.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
-metacontroller_pytorch-0.0.43.dist-info/RECORD,,
+metacontroller_pytorch-0.0.46.dist-info/METADATA,sha256=NL9ib9WWJn0IDhYHENp3L8blfIDPGdrHqCnB7EyV3IA,6816
+metacontroller_pytorch-0.0.46.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+metacontroller_pytorch-0.0.46.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
+metacontroller_pytorch-0.0.46.dist-info/RECORD,,