Commit Graph

  • 8d60ac3ffc [vizualisation] Add pagination for many episodes (#776) Mishig 2025-02-26 19:23:37 +01:00
  • 731fb6ebaf Fix import Simon Alibert 2025-02-26 19:02:15 +01:00
  • 13e124302f Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_25_refactor_robots Simon Alibert 2025-02-26 18:49:18 +01:00
  • 59bdd29106 Move more files & objects around Simon Alibert 2025-02-26 18:48:58 +01:00
  • 659ec4434d Fix nightly (#775) Simon Alibert 2025-02-26 16:36:03 +01:00
  • 124829104b Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_25_refactor_robots Simon Alibert 2025-02-26 16:26:03 +01:00
  • 21cd2940a9 Reorganize files Simon Alibert 2025-02-26 16:22:07 +01:00
  • da265ca920 Add pr style bot (#772) Simon Alibert 2025-02-25 23:52:25 +01:00
  • a1809ad3de Add typos checks (#770) Simon Alibert 2025-02-25 23:51:15 +01:00
  • 86e8c1d997 supporting accelerate user/mshukor/2025_02_25_accelerate mshukor 2025-02-25 21:38:17 +01:00
  • 1df9ee4f2d Add memory optimization option to ReplayBuffer AdilZouitine 2025-02-25 19:04:58 +00:00
  • 8699a28be0 [QOL] Enable teleoperation during environment reset (#725) Jannik Grothusen 2025-02-25 19:28:26 +01:00
  • 65db5afe1c fixes in 7_get_started_with_real_robot.md (#677) Raul Garreta 2025-02-25 10:03:29 -08:00
  • 75d5fa4604 Optimizing Dockerfile (#751) Youssef Bayouli 2025-02-25 18:42:35 +01:00
  • e64fad2224 Fix the URL to setup hardware Aloha Stationary in the example document (#766) Yongjin Cho 2025-02-26 02:33:32 +09:00
  • eecf32e77a feat: Add root directory option for dataset configuration (#765) Haskely 2025-02-26 00:27:36 +08:00
  • 5b4a7aa81d Add storage device parameter to replay buffer initialization AdilZouitine 2025-02-25 15:30:39 +00:00
  • 3354d919fc LeRobotDataset v2.1 (#711) Simon Alibert 2025-02-25 15:27:29 +01:00
  • ef8d943e54 Refactor ReplayBuffer with tensor-based storage and improved sampling efficiency AdilZouitine 2025-02-25 14:26:44 +00:00
  • aca464ca72 Add mobile so100 (#724) Pepijn 2025-02-25 09:06:50 +01:00
  • 42a038173f Update ManiSkill configuration and replay buffer to support truncation and dataset handling AdilZouitine 2025-02-24 16:53:37 +00:00
  • 3daab2acbb Add upload_large_folder Remi Cadene 2025-02-23 18:19:12 +00:00
  • c36d2253d0 Aggregate works Remi Cadene 2025-02-23 18:18:46 +00:00
  • e2e6f6e666 Add auto_downsample_height_width Remi Cadene 2025-02-23 18:15:39 +00:00
  • ff0029f84b aggregate works Remi Cadene 2025-02-22 15:33:47 +00:00
  • 39ad2d16d4 let's go Remi Cadene 2025-02-22 11:12:39 +00:00
  • 689c5efc72 optimize shard Remi Cadene 2025-02-22 10:13:09 +00:00
  • eda0b996cd new dir Remi Cadene 2025-02-21 23:56:44 +00:00
  • 15e7a9d541 before new launch from scratch Remi Cadene 2025-02-21 23:14:22 +00:00
  • 52fb4143b5 workers Remi Cadene 2025-02-21 13:08:21 +00:00
  • 546719137a Added caching function in the learner_server and modeling sac in order to limit the number of forward passes through the pretrained encoder when its frozen. Added tensordict dependencies Updated the version of torch and torchvision Michel Aractingi 2025-02-21 10:13:43 +00:00
  • 3ffe0cf0f4 [Port HIL-SERL] Adjust Actor-Learner architecture & clean up dependency management for HIL-SERL (#722) Eugene Mironov 2025-02-21 16:29:00 +07:00
  • 93c80b2cb1 rm brake Remi Cadene 2025-02-20 23:24:03 +00:00
  • 5fbbaa1bc0 fix No such file or directory error Remi Cadene 2025-02-20 23:04:58 +00:00
  • 71d1f5e2c9 WIP Remi Cadene 2025-02-20 23:04:31 +00:00
  • b520941cd9 Merge remote-tracking branch 'origin/user/aliberts/2025_02_10_dataset_v2.1' into user/rcadene/2025_02_19_port_openx Remi Cadene 2025-02-20 17:34:13 +00:00
  • a9e912a05c Sub threading for multiprocessing user/michel-aractingi/2024-02-21-hilserl-threading-to-mp Michel Aractingi 2025-02-20 17:21:55 +00:00
  • ff82367c62 Refactor SAC policy with performance optimizations and multi-camera support AdilZouitine 2025-02-20 17:14:27 +00:00
  • 64ed5258e6 Fix batch convert Simon Alibert 2025-02-20 09:00:14 +01:00
  • 392a8c32a7 Improve doc Simon Alibert 2025-02-20 08:24:41 +01:00
  • ff47c0b0d3 - 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. Michel Aractingi 2025-02-19 16:22:51 +00:00
  • 969ef745a2 Remove dataset consolidate (#752) Simon Alibert 2025-02-19 16:02:54 +01:00
  • 6fe42a72db Add tag Simon Alibert 2025-02-19 15:01:44 +01:00
  • 2487228ea7 Use HF_HOME env variable (#753) Simon Alibert 2025-02-19 14:49:46 +01:00
  • 76436ca1de Merge remote-tracking branch 'tavish9_lerobot_openx/main' into user/rcadene/2025_02_19_port_openx Remi Cadene 2025-02-19 12:58:18 +00:00
  • fbf2f2222a Remove local_files_only and use codebase_version instead of branches (#734) Simon Alibert 2025-02-19 08:36:32 +01:00
  • 02bc4e03e0 support openx/rlds to lerobot Tavish 2025-02-18 22:25:58 +08:00
  • 8469d13681 Added possibility to cache the embedding of the images when the encoder choice is pretrained and frozen user/michel-aractingi/2024-02-18-hilserl-cache-embedding Michel Aractingi 2025-02-18 08:28:13 +00:00
  • 624eaf1175 Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_10_dataset_v2.1 Simon Alibert 2025-02-17 12:06:05 +01:00
  • fe483b1d0d Remove poetry.lock (#737) Simon Alibert 2025-02-17 12:03:16 +01:00
  • befa1fe9af Re-enable parameter push thread in learner server AdilZouitine 2025-02-17 10:26:33 +00:00
  • 446f434a8e Improve wandb logging and custom step tracking in logger AdilZouitine 2025-02-17 10:08:49 +00:00
  • ddeade077e Conform pyproject to PEP 621 (#621) Simon Alibert 2025-02-16 14:28:03 +01:00
  • aed3eb4a94 Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_10_dataset_v2.1 Simon Alibert 2025-02-15 15:56:24 +01:00
  • c4c2ce04e7 Update pre-commits (#733) Simon Alibert 2025-02-15 15:51:17 +01:00
  • 2cb0bf5d41 Add zizmor pre-commit (#732) Simon Alibert 2025-02-15 15:50:10 +01:00
  • 8426c64f42 Per-episode stats (#521) Simon Alibert 2025-02-15 15:47:16 +01:00
  • 2f3370e42f Add maniskill support. Co-authored-by: Michel Aractingi <michel.aractingi@gmail.com> AdilZouitine 2025-02-14 19:53:29 +00:00
  • 7c2bbee613 Validate features during add_frame + Add 2D-to-5D + Add string (#720) Remi 2025-02-14 19:59:48 +01:00
  • b86a2c0b47 Fix wandb logging (#730) Simon Alibert 2025-02-14 18:00:12 +01:00
  • 7ae368e983 Fixed bug in the action scale of the intervention actions and offline dataset actions. (scale by inverse delta) Michel Aractingi 2025-02-14 15:17:16 +01:00
  • 9d6886dd08 Add frame level task (#693) Remi 2025-02-14 14:22:22 +01:00
  • 36711d766a Modified crop_dataset_roi interface to automatically write the cropped parameters to a json file in the meta of the dataset Michel Aractingi 2025-02-14 12:32:45 +01:00
  • c574eb4984 Fixed eval.py on MPS (#702) Ilia Larchenko 2025-02-14 06:03:55 +07:00
  • c9e50bb9b1 Optimized the replay buffer from the memory side to store data on cpu instead of a gpu device and send the batches to the gpu. Michel Aractingi 2025-02-13 18:03:57 +01:00
  • 1e49cc4d60 Prevent resuming from hub (#726) Simon Alibert 2025-02-13 17:15:55 +01:00
  • 95de8e273d nit Michel Aractingi 2025-02-13 17:12:57 +01:00
  • b07d95f0dd removed uncomment in actor server Michel Aractingi 2025-02-13 16:53:33 +01:00
  • d9a70376d8 Changed the init_final value to center the starting mean and std of the policy Michel Aractingi 2025-02-13 16:42:43 +01:00
  • 0c32008466 Changed bounds for a new so100 robot Michel Aractingi 2025-02-13 15:43:30 +01:00
  • c462a478c7 Hardcoded some normalization parameters. TODO refactor Added masking actions on the level of the intervention actions and offline dataset Michel Aractingi 2025-02-13 14:27:14 +01:00
  • 459f22ed30 fix log_alpha in modeling_sac: change to nn.parameter added pretrained vision model in policy Michel Aractingi 2025-02-13 11:26:24 +01:00
  • dc086dc21f Added logging for interventions to monitor the rate of interventions through time Added an s keyboard command to force success in the case the reward classifier fails Michel Aractingi 2025-02-13 11:04:49 +01:00
  • b9217b06db Added possiblity to record and replay delta actions during teleoperation rather than absolute actions Michel Aractingi 2025-02-12 19:25:41 +01:00
  • e71095960f Fixes following #670 (#719) Simon Alibert 2025-02-12 12:53:55 +01:00
  • d67ca342e9 Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_10_dataset_v2.1 Simon Alibert 2025-02-11 17:17:39 +01:00
  • 6868c88ef1 [PORT-Hilserl] classifier fixes (#695) Yoel 2025-02-11 11:39:17 +01:00
  • a1d16fb400 [Port HIL-SERL] Add resnet-10 as default encoder for HIL-SERL (#696) Eugene Mironov 2025-02-11 17:37:00 +07:00
  • a7db3959f5 - Added JointMaskingActionSpace wrapper in gym_manipulator in order to select which joints will be controlled. For example, we can disable the gripper actions for some tasks. - Added Nan detection mechanisms in the actor, learner and gym_manipulator for the case where we encounter nans in the loop. - changed the non-blocking in the .to(device) functions to only work for the case of cuda because they were causing nans when running the policy on mps - Added some joint clipping and limits in the env, robot and policy configs. TODO clean this part and make the limits in one config file only. Michel Aractingi 2025-02-11 11:34:46 +01:00
  • 90e099b39f Remove offline training, refactor train.py and logging/checkpointing (#670) Simon Alibert 2025-02-11 10:36:06 +01:00
  • 57c9c21c39 Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_10_dataset_v2.1 Simon Alibert 2025-02-10 17:22:57 +01:00
  • 334deb985d Update CI trigger rules (#712) Simon Alibert 2025-02-10 17:22:15 +01:00
  • 38c14571cc Bump CODEBASE_VERSION Simon Alibert 2025-02-10 16:39:34 +01:00
  • b5f89439ff Added sac_real config file in the policym configs dir. Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com> Michel Aractingi 2025-02-10 16:08:13 +01:00
  • d51374ce12 Several fixes to move the actor_server and learner_server code from the maniskill environment to the real robot environment. Michel Aractingi 2025-02-10 16:03:39 +01:00
  • 8548a87bd4 Remove dataset tests artifacts (#701) Simon Alibert 2025-02-09 14:24:01 +01:00
  • b63738674c [HIL-SERL port] Add Reward classifier benchmark tracking to chose best visual encoder (#688) Eugene Mironov 2025-02-07 00:39:51 +07:00
  • 12525242ce - Added lerobot/scripts/server/gym_manipulator.py that contains all the necessary wrappers to run a gym-style env around the real robot. - Added lerobot/scripts/server/find_joint_limits.py to test the min and max angles of the motion you wish the robot to explore during RL training. - Added logic in manipulator.py to limit the maximum possible joint angles to allow motion within a predefined joint position range. The limits are specified in the yaml config for each robot. Checkout the so100.yaml. Michel Aractingi 2025-02-06 16:29:37 +01:00
  • 7d5a9530f7 fixed bug in crop_dataset_roi.py added missing buffer.pt in server dir Michel Aractingi 2025-02-05 18:22:50 +00:00
  • e0527b4a6b Added additional wrappers for the environment: Action repeat, keyboard interface, reset wrapper Tested the reset mechanism and keyboard interface and the convert wrapper on the robots. Michel Aractingi 2025-02-04 17:41:14 +00:00
  • 638d411cd3 Add Pi0 (#681) Remi 2025-02-04 18:01:04 +01:00
  • efb1982eec Added crop_dataset_roi.py that allows you to load a lerobotdataset -> crop its images -> create a new lerobot dataset with the cropped and resized images. Michel Aractingi 2025-02-03 17:48:35 +00:00
  • dd974529cf User/pepijn/2025 01 31 improved tutorial so100 (#666) Pepijn 2025-02-03 18:27:55 +01:00
  • 2211209be5 - Added base gym env class for the real robot environment. - Added several wrappers around the base gym env robot class. - Including: time limit, reward classifier, crop images, preprocess observations. - Added an interactive script crop_roi.py where the user can interactively select the roi in the observation images and return the correct crop values that will improve the policy and reward classifier performance. Michel Aractingi 2025-02-03 14:52:45 +00:00
  • 506821c7df - Refactor observation encoder in modeling_sac.py - added torch.compile to the actor and learner servers. - organized imports in train_sac.py - optimized the parameters push by not sending the frozen pre-trained encoder. Michel Aractingi 2025-01-31 16:45:52 +00:00
  • f1c8bfe01e [Port HIL-SERL] Add HF vision encoder option in SAC (#651) Yoel 2025-01-31 09:42:13 +01:00
  • 7c89bd1018 Cleaned learner_server.py. Added several block function to improve readability. Michel Aractingi 2025-01-31 08:33:33 +00:00
  • 367dfe51c6 Added support for checkpointing the policy. We can save and load the policy state dict, optimizers state, optimization step and interaction step Added functions for converting the replay buffer from and to LeRobotDataset. When we want to save the replay buffer, we convert it first to LeRobotDataset format and save it locally and vice-versa. Michel Aractingi 2025-01-30 17:39:41 +00:00
  • e856ffc91e Removed unnecessary time.sleep in the streaming server on the learner side Michel Aractingi 2025-01-29 16:31:38 +00:00
  • 9aabe212ea Added missing config files env/maniskill_example.yaml and policy/sac_maniskill.yaml that are necessary to run the lerobot implementation of sac with the maniskill baselines. Michel Aractingi 2025-01-29 16:07:32 +00:00