Aggregate policy sub-losses through MetricsTracker (#4024)

src/lerobot/scripts/lerobot_train.py

@@ -171,6 +171,9 @@ def update_policy(
     train_metrics.update_s = time.perf_counter() - start_time
     if torch.cuda.is_available():
         train_metrics.gpu_mem_gb = torch.cuda.max_memory_allocated() / (1024**3)
+    # Aggregate the policy's scalar outputs for logging and rank-reduction across the log window.
+    if output_dict:
+        train_metrics.update_metrics(output_dict)
     return train_metrics, output_dict
 
 
@@ -572,7 +575,7 @@ def train(cfg: TrainPipelineConfig, accelerator: "Accelerator | None" = None):
         batch = preprocessor(batch)
         train_tracker.dataloading_s = time.perf_counter() - start_time
 
-        train_tracker, output_dict = update_policy(
+        train_tracker, _ = update_policy(
             train_tracker,
             policy,
             batch,
@@ -605,9 +608,10 @@ def train(cfg: TrainPipelineConfig, accelerator: "Accelerator | None" = None):
                     train_tracker.samples_per_s = effective_batch_size / step_time
                 logging.info(train_tracker)
                 if wandb_logger:
+                    # Policy sub-losses (latent_loss, action_loss, ...) are aggregated into the
+                    # tracker by update_policy, so to_dict() already carries their windowed,
+                    # rank-reduced averages — no per-step output_dict passthrough needed.
                     wandb_log_dict = train_tracker.to_dict()
-                    if output_dict:
-                        wandb_log_dict.update(output_dict)
                     # Log sample weighting statistics if enabled
                     if sample_weighter is not None:
                         weighter_stats = sample_weighter.get_stats()

src/lerobot/utils/logging_utils.py

@@ -104,6 +104,7 @@ class MetricsTracker:
         "episodes",
         "epochs",
         "accelerator",
+        "_caller_metrics",
     ]
 
     def __init__(
@@ -129,6 +130,9 @@ class MetricsTracker:
         self.episodes = self.samples / self._avg_samples_per_ep
         self.epochs = self.samples / self._num_frames
         self.accelerator = accelerator
+        # Meter names the caller registered up front. update_metrics() leaves these untouched, so a
+        # policy that echoes e.g. "loss" in its output dict can't clobber the aggregated meter.
+        self._caller_metrics: set[str] = set(self.metrics)
 
     def __getattr__(self, name: str) -> int | dict[str, AverageMeter] | AverageMeter | Any:
         if name in self.__dict__:
@@ -156,6 +160,21 @@ class MetricsTracker:
         self.episodes = self.samples / self._avg_samples_per_ep
         self.epochs = self.samples / self._num_frames
 
+    def update_metrics(self, values: dict[str, Any]) -> None:
+        """Accumulate a dict of scalar metrics, auto-registering a meter for each new key.
+
+        Non-numeric values and bools are ignored.
+        Caller-registered metrics (those passed to the constructor) are never overridden.
+        """
+        for name, value in values.items():
+            if isinstance(value, bool) or not isinstance(value, (int, float)):
+                continue
+            if name in self._caller_metrics:
+                continue
+            if name not in self.metrics:
+                self.metrics[name] = AverageMeter(name, ":.3f", reduction="mean")
+            self.metrics[name].update(float(value))
+
     def reduce_across_ranks(self) -> None:
         """
         Synchronises the running averages of every metric whose ``reduction`` is not ``"none"``