metacontroller-pytorch 0.0.16__py3-none-any.whl → 0.0.17__py3-none-any.whl

metacontroller/metacontroller.py

@@ -57,7 +57,8 @@ MetaControllerOutput = namedtuple('MetaControllerOutput', (
     'prev_hiddens',
     'action_dist',
     'actions',
-    'kl_loss'
+    'kl_loss',
+    'switch_loss'
 ))
 
 class MetaController(Module):
@@ -173,7 +174,7 @@ class MetaController(Module):
 
         # need to encourage normal distribution
 
-        kl_loss = self.zero
+        kl_loss = switch_loss = self.zero
 
         if discovery_phase:
             mean, log_var = action_dist.unbind(dim = -1)
@@ -188,6 +189,10 @@ class MetaController(Module):
             kl_loss = kl_loss * switch_beta
             kl_loss = kl_loss.sum(dim = -1).mean()
 
+            # encourage less switching
+
+            switch_loss = switch_beta.mean()
+
         # maybe hard switch, then use associative scan
 
         if hard_switch:
@@ -220,7 +225,7 @@ class MetaController(Module):
             next_switch_gated_action
         )
 
-        return modified_residual_stream, MetaControllerOutput(next_hiddens, action_dist, sampled_action, kl_loss)
+        return modified_residual_stream, MetaControllerOutput(next_hiddens, action_dist, sampled_action, kl_loss, switch_loss)
 
 # main transformer, which is subsumed into the environment after behavioral cloning
 
@@ -357,7 +362,7 @@ class Transformer(Module):
 
             action_recon_loss = self.action_readout.calculate_loss(dist_params, target_action_ids)
 
-            return action_recon_loss, next_meta_hiddens.kl_loss
+            return action_recon_loss, next_meta_hiddens.kl_loss, next_meta_hiddens.switch_loss
 
         # returning
 

{metacontroller_pytorch-0.0.16.dist-info → metacontroller_pytorch-0.0.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metacontroller-pytorch
-Version: 0.0.16
+Version: 0.0.17
 Summary: Transformer Metacontroller
 Project-URL: Homepage, https://pypi.org/project/metacontroller/
 Project-URL: Repository, https://github.com/lucidrains/metacontroller

metacontroller_pytorch-0.0.17.dist-info/RECORD

@@ -0,0 +1,6 @@
+metacontroller/__init__.py,sha256=lj7IOGpN--qMxJWbB-4SGqoPXG7Hd4mgtToTRSyTZ58,57
+metacontroller/metacontroller.py,sha256=blxDztbtXyP3cNbjnM3fEw_KZdLFJp_l1Sub6-7zIKg,12041
+metacontroller_pytorch-0.0.17.dist-info/METADATA,sha256=_8hYYTO_ME23kgZXqSfhA1XXAA8W877F-AL8amA7LKM,3741
+metacontroller_pytorch-0.0.17.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+metacontroller_pytorch-0.0.17.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
+metacontroller_pytorch-0.0.17.dist-info/RECORD,,

metacontroller_pytorch-0.0.16.dist-info/RECORD

@@ -1,6 +0,0 @@
-metacontroller/__init__.py,sha256=lj7IOGpN--qMxJWbB-4SGqoPXG7Hd4mgtToTRSyTZ58,57
-metacontroller/metacontroller.py,sha256=BT7GH8F9NkEIYLEueBkkZ8glQ3Oht1FRoV84SIaTWdQ,11878
-metacontroller_pytorch-0.0.16.dist-info/METADATA,sha256=eyECb3994X58zyExLnnffMl3pOoMlIb-WAUhepIt0r8,3741
-metacontroller_pytorch-0.0.16.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-metacontroller_pytorch-0.0.16.dist-info/licenses/LICENSE,sha256=1yCiA9b5nhslTavxPjsQAO-wpOnwJR9-l8LTVi7GJuk,1066
-metacontroller_pytorch-0.0.16.dist-info/RECORD,,