admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-26 11:16:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Khalil Meftah
2026-03-12 15:23:42 +01:00
parent 0b992cfbd6
commit 445ffae5ce
14 changed files with 31 additions and 3209 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/dataset/slurm_compute_rabc.py
+1 -1
View File
@@ -69,7 +69,7 @@ class ComputeProgressShards(PipelineStep):
import torch
from tqdm import tqdm
from lerobot.policies.sarm.compute_rabc_weights import (
from lerobot.rewards.sarm.compute_rabc_weights import (
generate_all_frame_indices,
interpolate_progress,
load_sarm_resources,
examples/tutorial/rl/hilserl_example.py
+1 -1
View File
@@ -11,7 +11,7 @@ from lerobot.datasets.utils import hw_to_dataset_features
from lerobot.envs.configs import HILSerlProcessorConfig, HILSerlRobotEnvConfig
from lerobot.policies.sac.configuration_sac import SACConfig
from lerobot.policies.sac.modeling_sac import SACPolicy
from lerobot.policies.sac.reward_model.modeling_classifier import Classifier
from lerobot.rewards.classifier.modeling_classifier import Classifier
from lerobot.rl.buffer import ReplayBuffer
from lerobot.rl.gym_manipulator import make_robot_env
from lerobot.robots.so_follower import SO100FollowerConfig
examples/tutorial/rl/reward_classifier_example.py
+4 -3
View File
@@ -1,8 +1,9 @@
import torch
from lerobot.datasets.lerobot_dataset import LeRobotDataset
from lerobot.policies.factory import make_policy, make_pre_post_processors
from lerobot.policies.sac.reward_model.configuration_classifier import RewardClassifierConfig
from lerobot.policies.factory import make_policy
from lerobot.rewards.classifier.configuration_classifier import RewardClassifierConfig
from lerobot.rewards.factory import make_reward_pre_post_processors
def main():
@@ -26,7 +27,7 @@ def main():
# 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)
preprocessor, _ = make_reward_pre_post_processors(config, dataset_stats=dataset.meta.stats)
classifier_id = "<user>/reward_classifier_hil_serl_example"