fix(bug): Fix policy renaming ValueError during training (#2278)

* fixes

* style

* Update src/lerobot/policies/factory.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Signed-off-by: Jade Choghari <chogharijade@gmail.com>

* style

* add review fixes

---------

Signed-off-by: Jade Choghari <chogharijade@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

src/lerobot/scripts/lerobot_train.py

@@ -203,6 +203,7 @@ def train(cfg: TrainPipelineConfig, accelerator: Accelerator | None = None):
     policy = make_policy(
         cfg=cfg.policy,
         ds_meta=dataset.meta,
+        rename_map=cfg.rename_map,
     )
 
     # Wait for all processes to finish policy creation before continuing
@@ -224,6 +225,9 @@ def train(cfg: TrainPipelineConfig, accelerator: Accelerator | None = None):
                 "norm_map": policy.config.normalization_mapping,
             },
         }
+        processor_kwargs["preprocessor_overrides"]["rename_observations_processor"] = {
+            "rename_map": cfg.rename_map
+        }
         postprocessor_kwargs["postprocessor_overrides"] = {
             "unnormalizer_processor": {
                 "stats": dataset.meta.stats,