- Fixed big issue in the loading of the policy parameters sent by the learner to the actor -- pass only the actor to the update_policy_parameters and remove strict=False

- Fixed big issue in the normalization of the actions in the `forward` function of the critic -- remove the `torch.no_grad` decorator in `normalize.py` in the normalization function
- Fixed performance issue to boost the optimization frequency by setting the storage device to be the same as the device of learning.

Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>

lerobot/scripts/server/learner_server.py

@@ -142,6 +142,7 @@ def initialize_replay_buffer(cfg: DictConfig, logger: Logger, device: str) -> Re
             capacity=cfg.training.online_buffer_capacity,
             device=device,
             state_keys=cfg.policy.input_shapes.keys(),
+            storage_device=device
         )
 
     dataset = LeRobotDataset(