Commit Graph

  • 875662f16b 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
  • 87c7eca582 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
  • 179ee3b1f6 - 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
  • b29401e4e2 - 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
  • faab32fe14 [Port HIL-SERL] Add HF vision encoder option in SAC (#651) Yoel 2025-01-31 09:42:13 +01:00
  • c620b0878f Cleaned learner_server.py. Added several block function to improve readability. Michel Aractingi 2025-01-31 08:33:33 +00:00
  • 2023289ce8 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
  • 9afd093030 Removed unnecessary time.sleep in the streaming server on the learner side Michel Aractingi 2025-01-29 16:31:38 +00:00
  • f3c4d6e1ec 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
  • 18207d995e - Added additional logging information in wandb around the timings of the policy loop and optimization loop. - Optimized critic design that improves the performance of the learner loop by a factor of 2 - Cleaned the code and fixed style issues Michel Aractingi 2025-01-29 15:50:46 +00:00
  • a0a81c0c12 FREEDOM, added back the optimization loop code in learner_server.py Ran experiment with pushcube env from maniskill. The learning seem to work. Michel Aractingi 2025-01-28 17:25:49 +00:00
  • ef64ba91d9 Added server directory in lerobot/scripts that contains scripts and the protobuf message types to split training into two processes, acting and learning. The actor rollouts the policy and collects interaction data while the learner recieves the data, trains the policy and sends the updated parameters to the actor. The two scripts are ran simultaneously Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com> Michel Aractingi 2025-01-28 15:52:03 +00:00
  • 83dc00683c Stable version of rlpd + drq AdilZouitine 2025-01-22 09:00:16 +00:00
  • 5b92465e38 Add type annotations and restructure SACConfig class fields AdilZouitine 2025-01-21 09:51:12 +00:00
  • 4b78ab2789 Change SAC policy implementation with configuration and modeling classes Adil Zouitine 2025-01-17 09:39:04 +01:00
  • bd8c768f62 SAC works Adil Zouitine 2025-01-14 11:34:52 +01:00
  • 1e9bafc852 [WIP] correct sac implementation Adil Zouitine 2025-01-13 17:54:11 +01:00
  • 921ed960fb Add rlpd tricks Adil Zouitine 2025-01-15 15:49:24 +01:00
  • 67b64e445b SAC works Adil Zouitine 2025-01-14 11:34:52 +01:00
  • 6c8023e702 remove breakpoint Adil Zouitine 2025-01-13 17:58:00 +01:00
  • b495b19a6a [WIP] correct sac implementation Adil Zouitine 2025-01-13 17:54:11 +01:00
  • 6139df553d Extend reward classifier for multiple camera views (#626) Michel Aractingi 2025-01-13 13:57:49 +01:00
  • b68730474a [Port HIL_SERL] Final fixes for the Reward Classifier (#598) Eugene Mironov 2025-01-06 17:34:00 +07:00
  • 764925e4a2 added temporary fix for missing task_index key in online environment Michel Aractingi 2024-12-30 13:47:28 +00:00
  • 7bb142b707 split encoder for critic and actor Michel Aractingi 2024-12-29 23:59:39 +00:00
  • 2c2ed084cc style fixes Michel Aractingi 2024-12-29 14:35:21 +00:00
  • 91fefdecfa Refactor SAC configuration and policy for improved action sampling and stability KeWang1017 2024-12-29 12:30:39 +00:00
  • 70e3b9248c Refine SAC configuration and policy for enhanced performance KeWang1017 2024-12-28 22:11:34 +00:00
  • 0ecf40d396 Refactor SACPolicy for improved action sampling and standard deviation handling KeWang1017 2024-12-28 18:07:15 +00:00
  • a113daa81e trying to get sac running KeWang1017 2024-12-26 23:38:46 +00:00
  • 80b86e9bc3 Added normalization schemes and style checks Michel Aractingi 2024-12-29 12:51:21 +00:00
  • 9dafad15e6 added optimizer and sac to factory.py Michel Aractingi 2024-12-23 14:12:03 +01:00
  • d96edbf5ac [HIL-SERL PORT] Fix linter issues (#588) Eugene Mironov 2024-12-23 16:44:29 +07:00
  • 6340d9d17c [Port Hil-SERL] Add unit tests for the reward classifier & fix imports & check script (#578) Eugene Mironov 2024-12-23 16:43:55 +07:00
  • 66268fcf85 added comments from kewang Michel Aractingi 2024-12-17 18:03:46 +01:00
  • a5228a0dfe Enhance SAC configuration and policy with new parameters and subsampling logic KeWang1017 2024-12-17 15:58:04 +00:00
  • dbadaae28b Port SAC WIP (#581) KeWang 2024-12-17 13:26:17 +00:00
  • 44536d1f0c completed losses Michel Aractingi 2024-12-12 11:45:30 +01:00
  • 69b6de46d7 nit in control_robot.py Michel Aractingi 2024-12-11 00:30:33 +01:00
  • 399f834788 Update lerobot/scripts/train_hilserl_classifier.py Michel Aractingi 2024-12-11 00:22:10 +01:00
  • df57d372d6 Fixup Eugene Mironov 2024-12-17 02:42:53 +07:00
  • 76234b7d14 Add human intervention mechanism and eval_robot script to evaluate policy on the robot (#541) Michel Aractingi 2024-12-09 19:17:47 +01:00
  • 58cc445921 Reward classifier and training (#528) Yoel 2024-12-09 10:21:50 +01:00
  • b568de35ad fix(datasets): cast imgs_dir as Path (#915) Steven Palma 2025-03-28 18:08:12 +01:00
  • ae9c81ac39 fix(docs): correct spelling of 'ffmpeg' in installation instructions (#914) Yongjin Cho 2025-03-29 01:43:33 +09:00
  • 78fd1a1e04 chore(docs): update docs (#911) Steven Palma 2025-03-27 09:55:06 +01:00
  • 90533e6b9f fix(docs): hot-fix updating installation instructions after #883 (#907) Steven Palma 2025-03-26 13:21:40 +01:00
  • 051a52a4ce Remove todo Simon Alibert 2025-03-25 21:32:30 +01:00
  • 2292b514aa Fix calibration functions Simon Alibert 2025-03-25 17:58:54 +01:00
  • 1f1a01a798 Rename CalibrationMode -> MotorNormMode Simon Alibert 2025-03-25 17:42:18 +01:00
  • faa476f0d2 Remove deprecated scripts Simon Alibert 2025-03-25 17:33:05 +01:00
  • 5130b69ece Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_25_refactor_robots Simon Alibert 2025-03-25 16:25:47 +01:00
  • aed85241b7 Merge branch 'user/aliberts/2025_02_25_refactor_robots' of github.com:huggingface/lerobot into user/aliberts/2025_02_25_refactor_robots Simon Alibert 2025-03-25 16:24:40 +01:00
  • 21c3ac42ee Add new calibration method for robot refactor (#896) Pepijn 2025-03-25 16:24:04 +01:00
  • 2d3a5fb2be (WIP) _async_read Simon Alibert 2025-03-25 15:37:18 +01:00
  • a631e4c11c Rename idx -> id_ Simon Alibert 2025-03-25 15:36:36 +01:00
  • 222d6f104e Rename idx -> id_ Simon Alibert 2025-03-25 14:20:12 +01:00
  • 7a3b424cd3 Add calibration Simon Alibert 2025-03-25 14:13:55 +01:00
  • 2c22f7d76d Add offline mode in the configuration for wandb logging (#897) AlexC 2025-03-25 13:44:49 +01:00
  • 374d4351fd chore(dummy): add comments + better visualization feat/add_rerun Steven Palma 2025-03-25 13:02:11 +01:00
  • af295fadb5 Fix imports Simon Alibert 2025-03-25 12:48:58 +01:00
  • 9644e2b086 Fix visualize_motors_bus Simon Alibert 2025-03-25 12:47:44 +01:00
  • 6ccf083127 Update so100 imports Simon Alibert 2025-03-25 12:32:38 +01:00
  • bb774e7acd Update Koch imports Simon Alibert 2025-03-25 12:31:51 +01:00
  • dcbbeab80b Move DriveMode & TorqueMode Simon Alibert 2025-03-25 12:30:07 +01:00
  • b71ac34214 Add test_motors_bus Simon Alibert 2025-03-25 12:11:56 +01:00
  • a774af2eab fix pi0 action padding name (#893) Qizhi Chen 2025-03-25 18:24:46 +08:00
  • c237d1379e Update tests Simon Alibert 2025-03-25 11:12:52 +01:00
  • cf963eb1b0 Ensure motors exist at connection time Simon Alibert 2025-03-25 11:12:26 +01:00
  • 4293b6a4fb Fix feetech ping tests Simon Alibert 2025-03-25 07:26:34 +01:00
  • 725b446ad6 fix(deps): constrain PyAV version to resolve OpenCV-python ffmpeg version conflict (#883) Steven Palma 2025-03-24 23:40:22 +01:00
  • 7a75bb9f61 Improve errors Simon Alibert 2025-03-24 21:13:26 +01:00
  • 0c1d4cb323 Rename idx -> id_ Simon Alibert 2025-03-24 20:58:56 +01:00
  • c6212d585d Add raw_values option Simon Alibert 2025-03-24 20:56:58 +01:00
  • 7c8ab8e2d6 Implement feetech broadcast ping Simon Alibert 2025-03-24 20:46:36 +01:00
  • 1de75c46c0 Return models (str) with pings Simon Alibert 2025-03-24 20:42:43 +01:00
  • 4f3eaff2bd [skip ci] feat: implement rerun v0.1 Steven Palma 2025-03-24 17:11:59 +01:00
  • 4ad109cff8 Merge remote-tracking branch 'origin/main' into user/aliberts/2025_02_25_refactor_robots Simon Alibert 2025-03-24 13:25:29 +01:00
  • 8994252019 Add _configure_motors & move ping methods Simon Alibert 2025-03-24 12:19:03 +01:00
  • 9832daf08d Fix dict Simon Alibert 2025-03-24 12:16:54 +01:00
  • 39d8f45810 Privatize methods & renames Simon Alibert 2025-03-24 11:57:12 +01:00
  • 30fcd3d417 Update so100 Simon Alibert 2025-03-23 20:15:47 +01:00
  • 039b437ef0 Update ensure_safe_goal_position Simon Alibert 2025-03-23 19:43:58 +01:00
  • 7582a0a2b0 Caps dxl OperatingMode Simon Alibert 2025-03-23 19:42:21 +01:00
  • 25388d0947 Add feetech operating modes Simon Alibert 2025-03-23 19:41:46 +01:00
  • 7152bc8aa7 Update Koch Simon Alibert 2025-03-23 19:32:26 +01:00
  • 5b46dc0b6a Add is_connected in robots and teleops Simon Alibert 2025-03-23 19:26:10 +01:00
  • 4273f1f384 Add dxl operating modes Simon Alibert 2025-03-23 19:25:21 +01:00
  • 97194bf7f3 Nit Simon Alibert 2025-03-23 17:05:08 +01:00
  • 0ac026b521 Remove test skips & fix docstrings Simon Alibert 2025-03-23 17:04:30 +01:00
  • ff7cfdaf40 Move mock_serial patch to dedicated file Simon Alibert 2025-03-23 17:03:04 +01:00
  • 57c97762e1 Simplify _is_comm_success & _is_error Simon Alibert 2025-03-23 16:52:29 +01:00
  • a38bb15e79 Add feetech write test Simon Alibert 2025-03-23 16:48:32 +01:00
  • 3ceaee999d Refactor feetech tests by functionality Simon Alibert 2025-03-23 16:25:12 +01:00
  • d485dc1313 Refactor _is_comm_success Simon Alibert 2025-03-23 16:15:53 +01:00
  • 329d103453 Add dxl write test Simon Alibert 2025-03-23 16:12:24 +01:00
  • 9f46a3d8f9 Refactor dxl tests by functionality Simon Alibert 2025-03-23 16:11:24 +01:00
  • c9ca9e4316 Rename tests Simon Alibert 2025-03-23 13:32:08 +01:00
  • 5a57e6f4a7 Rename read/write -> sync_read/write, refactor, add write Simon Alibert 2025-03-23 13:25:45 +01:00
  • a2f5c34625 Simplify split_int_bytes Simon Alibert 2025-03-23 11:55:39 +01:00