Reward models refactor (#3142)

* feat(rewards): add RewardModelConfig and PreTrainedRewardModel base classes

* refactor(rewards): migrate Classifier from policies/sac/reward_model/ to rewards/classifier/

* refactor(rewards): migrate SARM from policies/sarm/ to rewards/sarm/

* refactor(rewards): add rewards/factory.py and remove reward model code from policies/factory.py

* refactor(rewards): update imports and delete old reward model locations

* test(rewards): add reward model tests and update existing test imports

* fix(rewards): restore full Classifier and SARM implementations

* test(rewards): restore missing CUDA and mixed precision classifier processor tests

* refactor(lerobot_train.py): remove rabc specific configuration and replace it with a generic samplerweight class in lerobot_train

* refactor(lerobot_train.py): add missing sampling weight script

* linter + missing files

* add testing for sampl weighter

* revert some useless changes, improve typing

* update docs

* add automatic detection of the progress path

* remove type exp

* improve comment

* fix: move rabc.py to rewards/sarm/ and update import paths

* refactor(imports): update reward model imports to new module structure

* refactor(imports): update reward model imports to reflect new module structure

* refactor(imports): conditionally import pandas based on availability

* feat(configs): add reward_model field to TrainPipelineConfig and Hub fields to RewardModelConfig

* refactor(policies): remove reward model branches from policy factory and __init__

* refactor(rewards): expand __init__ facade and fix SARMConfig __post_init__ crash

* feat(train): route reward model training through rewards/factory instead of policies/factory

* refactor(train): streamline reward model training logic

* fix(rewards): ensure FileNotFoundError is raised for missing config_file

* refactor(train): update __get_path_fields__ to include reward_model for config loading

* refactor(classifier): remove redundant input normalization in predict_reward method

* fix(train): raise ValueError for non-trainable reward models in train function

* refactor(pretrained_rm): add model card template

* refactor(tests): reward models

* refactor(sarm): update reset method and remove unused action prediction methods

* refactor(wandb): differentiate tags for reward model and policy training in cfg_to_group function

* fix(train): raise ValueError for PEFT usage in reward model training

* refactor(rewards): enhance RewardModelConfig with device handling and delta indices properties

---------

Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>

examples/tutorial/rl/reward_classifier_example.py

@@ -1,7 +1,7 @@
 import torch
 
 from lerobot.datasets import LeRobotDataset
-from lerobot.policies import RewardClassifierConfig, make_policy, make_pre_post_processors
+from lerobot.rewards import RewardClassifierConfig, make_reward_model, make_reward_pre_post_processors
 
 
 def main():
@@ -22,10 +22,10 @@ def main():
         model_name="microsoft/resnet-18",
     )
 
-    # Make policy, preprocessor, and optimizer
-    policy = make_policy(config, ds_meta=dataset.meta)
-    optimizer = config.get_optimizer_preset().build(policy.parameters())
-    preprocessor, _ = make_pre_post_processors(policy_cfg=config, dataset_stats=dataset.meta.stats)
+    # Make reward model, preprocessor, and optimizer
+    reward_model = make_reward_model(config, dataset_stats=dataset.meta.stats)
+    optimizer = config.get_optimizer_preset().build(reward_model.parameters())
+    preprocessor, _ = make_reward_pre_post_processors(config, dataset_stats=dataset.meta.stats)
 
     classifier_id = "<user>/reward_classifier_hil_serl_example"
 
@@ -42,7 +42,7 @@ def main():
             batch = preprocessor(batch)
 
             # Forward pass
-            loss, output_dict = policy.forward(batch)
+            loss, output_dict = reward_model.forward(batch)
 
             # Backward pass and optimization
             optimizer.zero_grad()
@@ -58,8 +58,8 @@ def main():
 
     print("Training finished!")
 
-    # You can now save the trained policy.
-    policy.push_to_hub(classifier_id)
+    # You can now save the trained reward model.
+    reward_model.push_to_hub(classifier_id)
 
 
 if __name__ == "__main__":