Commit Graph

  • 42618f4bd6 - 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
  • 36576c958f 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
  • 322a78a378 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
  • d75b44f89f Stable version of rlpd + drq AdilZouitine 2025-01-22 09:00:16 +00:00
  • 1fb03d4cf2 Add type annotations and restructure SACConfig class fields AdilZouitine 2025-01-21 09:51:12 +00:00
  • 7d2970fdfe Change SAC policy implementation with configuration and modeling classes Adil Zouitine 2025-01-17 09:39:04 +01:00
  • 8105efb338 Add rlpd tricks Adil Zouitine 2025-01-15 15:49:24 +01:00
  • c1d4bf4b63 SAC works Adil Zouitine 2025-01-14 11:34:52 +01:00
  • 86df8a433d remove breakpoint Adil Zouitine 2025-01-13 17:58:00 +01:00
  • 956c547254 [WIP] correct sac implementation Adil Zouitine 2025-01-13 17:54:11 +01:00
  • be965019bd Add rlpd tricks Adil Zouitine 2025-01-15 15:49:24 +01:00
  • a0a50de8c9 SAC works Adil Zouitine 2025-01-14 11:34:52 +01:00
  • c86dace4c2 remove breakpoint Adil Zouitine 2025-01-13 17:58:00 +01:00
  • 472a7f58ad [WIP] correct sac implementation Adil Zouitine 2025-01-13 17:54:11 +01:00
  • 068efce3f8 Fix for the issue https://github.com/huggingface/lerobot/issues/638 (#639) Pradeep Kadubandi 2025-01-15 01:50:38 -08:00
  • df7310ea40 fixes to SO-100 readme (#600) Philip Fung 2025-01-10 02:30:01 -08:00
  • 100f54ee07 [viz] Fixes & updates to html visualizer (#617) Mishig 2025-01-09 11:39:54 +01:00
  • c2f7af3339 typo fix: batch_convert_dataset_v1_to_v2.py (#615) CharlesCNorton 2025-01-09 03:57:45 -05:00
  • a1b5d0faf2 fix(visualise): use correct language description for each episode id (#604) Ville Kuosmanen 2025-01-09 08:39:48 +00:00
  • d6498150bf fix(docs): typos in benchmark readme.md (#614) CharlesCNorton 2025-01-09 03:35:27 -05:00
  • 31c34a4a49 Fix Quality workflow (#622) Simon Alibert 2025-01-08 13:35:11 +01:00
  • b1cfb6a710 Update README.md (#612) CharlesCNorton 2025-01-03 10:19:37 -05:00
  • 4a43c83522 Fix broken create_lerobot_dataset_card (#590) Eugene Mironov 2024-12-23 21:05:59 +07:00
  • 0a4e9e25d0 [vizualizer] for LeRobodDataset V2 (#576) Mishig 2024-12-20 16:26:23 +01:00
  • 43e079f73e Fix nightly tests docker images (#675) Simon Alibert 2025-02-02 13:59:33 +01:00
  • 6674e36824 Fix Docker cpu/gpu builds (#667) Simon Alibert 2025-02-01 12:06:11 +01:00
  • ae9605f03c fix setting motor id with new dataclass config (#668) Pepijn 2025-01-31 20:48:46 +01:00
  • 3c0a209f9f Simplify configs (#550) Simon Alibert 2025-01-31 13:57:37 +01:00
  • 1ee1acf8ad Comply with torchvision 0.21 custom transforms (#665) Simon Alibert 2025-01-30 22:06:11 +01:00
  • c4d912a241 Check for "/" in feature names (#660) Thomas Lips 2025-01-29 21:54:49 +01:00
  • 4323bdce22 updating config instructions for koch 1v1 motors (#658) Morgan Redfield 2025-01-28 07:20:33 -05:00
  • 5daa45436d Fix typos in lerobot/scripts/visualize_dataset.py (#656) HUANG TZU-CHUN 2025-01-28 20:07:10 +08:00
  • 4def6d6ac2 Fix cluster image (#653) Simon Alibert 2025-01-24 11:25:22 +01:00
  • daa1480a91 nit user/michel-aractingi/2025-01-21-server-client-arch Michel Aractingi 2025-01-22 09:45:05 +01:00
  • 71ec721e48 cleaned eval_on_robot.py; readded policy; fixed doc strings Michel Aractingi 2025-01-22 01:15:45 +01:00
  • bbb5ba0adf Extend reward classifier for multiple camera views (#626) Michel Aractingi 2025-01-13 13:57:49 +01:00
  • 844bfcf484 [Port HIL_SERL] Final fixes for the Reward Classifier (#598) Eugene Mironov 2025-01-06 17:34:00 +07:00
  • 13441f0d98 added temporary fix for missing task_index key in online environment Michel Aractingi 2024-12-30 13:47:28 +00:00
  • 41b377211c split encoder for critic and actor Michel Aractingi 2024-12-29 23:59:39 +00:00
  • 9ceb68ee90 Refine SAC configuration and policy for enhanced performance KeWang1017 2024-12-28 22:11:34 +00:00
  • d1baa5a82f trying to get sac running KeWang1017 2024-12-26 23:38:46 +00:00
  • 04da4dd3e3 Added normalization schemes and style checks Michel Aractingi 2024-12-29 12:51:21 +00:00
  • b0e2fcdba7 added optimizer and sac to factory.py Michel Aractingi 2024-12-23 14:12:03 +01:00
  • 1e2a757cd3 [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
  • ab842ba6ae nit in control_robot.py Michel Aractingi 2024-12-11 00:30:33 +01:00
  • 94a7221a94 Update lerobot/scripts/train_hilserl_classifier.py Michel Aractingi 2024-12-11 00:22:10 +01:00
  • 00dadcace0 LerobotDataset pushable to HF from any folder (#563) Claudio Coppola 2024-12-09 10:32:25 +00:00
  • 81a2f2958d Update 7_get_started_with_real_robot.md (#559) berjaoui 2024-12-09 00:17:49 +01:00
  • 68b4fb60ad Control simulated robot with real leader (#514) Michel Aractingi 2024-12-03 12:20:05 +01:00
  • 96b2b62377 Fix missing local_files_only in record/replay (#540) Remi 2024-12-03 10:53:21 +01:00
  • b5c98bbfd3 Refactor OpenX (#505) Michel Aractingi 2024-12-03 00:51:55 +01:00
  • 58e12cf2e8 Fixup Eugene Mironov 2024-12-17 02:42:53 +07:00
  • d8b5fae622 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
  • 67ac81d728 Reward classifier and training (#528) Yoel 2024-12-09 10:21:50 +01:00
  • b5f1ea3140 nit Michel Aractingi 2024-11-27 15:19:20 +01:00
  • 4d854a1513 Stable version of rlpd + drq origin/user/adil-zouitine/2025-1-7-port-hil-serl-new AdilZouitine 2025-01-22 09:00:16 +00:00
  • 87da655eab Add type annotations and restructure SACConfig class fields AdilZouitine 2025-01-21 09:51:12 +00:00
  • 6cc2cc896a set num workers to zero in compute stats, temporary fix to hanging code when iterating over dataloader user/michel-aractingi/2025-01-18-port-rlds-example Michel Aractingi 2025-01-20 11:02:37 +00:00
  • d8560b8d5f Bumprerun-sdk dependency to 0.21.0 (#618) Jochen Görtler 2025-01-20 09:50:11 +01:00
  • acc433d25d Added example script to port rlds/openx dataset formats Michel Aractingi 2025-01-18 10:49:26 +00:00
  • a8fda9c61a Change SAC policy implementation with configuration and modeling classes Adil Zouitine 2025-01-17 09:39:04 +01:00
  • 55505ff817 Add rlpd tricks Adil Zouitine 2025-01-15 15:49:24 +01:00
  • 20d31ab8e0 SAC works Adil Zouitine 2025-01-14 11:34:52 +01:00
  • e5b83aab5e remove breakpoint Adil Zouitine 2025-01-13 17:58:00 +01:00
  • a9d5f62304 [WIP] correct sac implementation Adil Zouitine 2025-01-13 17:54:11 +01:00
  • 72e1ed7058 Add rlpd tricks Adil Zouitine 2025-01-15 15:49:24 +01:00
  • d8e67a2609 SAC works Adil Zouitine 2025-01-14 11:34:52 +01:00
  • 50e12376de remove breakpoint Adil Zouitine 2025-01-13 17:58:00 +01:00
  • 73aa6c25f3 [WIP] correct sac implementation Adil Zouitine 2025-01-13 17:54:11 +01:00
  • 380b836eee Fix for the issue https://github.com/huggingface/lerobot/issues/638 (#639) Pradeep Kadubandi 2025-01-15 01:50:38 -08:00
  • f945641de9 added SM8512BL nepyope 2025-01-14 14:19:38 +01:00
  • 3bb5ed5e91 Extend reward classifier for multiple camera views (#626) Michel Aractingi 2025-01-13 13:57:49 +01:00
  • eec6796cb8 fixes to SO-100 readme (#600) Philip Fung 2025-01-10 02:30:01 -08:00
  • 5bd41a3dca added feetech failsafe comment nepyope 2025-01-09 18:14:01 +01:00
  • 25a8597680 [viz] Fixes & updates to html visualizer (#617) Mishig 2025-01-09 11:39:54 +01:00
  • b8b368310c typo fix: batch_convert_dataset_v1_to_v2.py (#615) CharlesCNorton 2025-01-09 03:57:45 -05:00
  • 5097cd900e fix(visualise): use correct language description for each episode id (#604) Ville Kuosmanen 2025-01-09 08:39:48 +00:00
  • bc16e1b497 fix(docs): typos in benchmark readme.md (#614) CharlesCNorton 2025-01-09 03:35:27 -05:00
  • 8f821ecad0 Fix Quality workflow (#622) Simon Alibert 2025-01-08 13:35:11 +01:00
  • c5bca1cf0f [Port HIL_SERL] Final fixes for the Reward Classifier (#598) Eugene Mironov 2025-01-06 17:34:00 +07:00
  • 4519016e67 Update README.md (#612) CharlesCNorton 2025-01-03 10:19:37 -05:00
  • 35de91ef2b added temporary fix for missing task_index key in online environment Michel Aractingi 2024-12-30 13:47:28 +00:00
  • ee306e2f9b split encoder for critic and actor Michel Aractingi 2024-12-29 23:59:39 +00:00
  • bae3b02928 style fixes Michel Aractingi 2024-12-29 14:35:21 +00:00
  • 5b4adc00bb Refactor SAC configuration and policy for improved action sampling and stability KeWang1017 2024-12-29 12:30:39 +00:00
  • 22fbc9ea4a Refine SAC configuration and policy for enhanced performance KeWang1017 2024-12-28 22:11:34 +00:00
  • ca74a13d61 Refactor SACPolicy for improved action sampling and standard deviation handling KeWang1017 2024-12-28 18:07:15 +00:00
  • 18a4598986 trying to get sac running KeWang1017 2024-12-26 23:38:46 +00:00
  • dc54d357ca Added normalization schemes and style checks Michel Aractingi 2024-12-29 12:51:21 +00:00
  • f996a13f70 Add test3 test4 Remi Cadene 2024-12-29 13:30:17 +01:00
  • 743ebfa7c1 Cremaillaire HF Remi Cadene 2024-12-24 11:33:55 +01:00
  • 59e2757434 Fix broken create_lerobot_dataset_card (#590) Eugene Mironov 2024-12-23 21:05:59 +07:00
  • 08ec971086 added optimizer and sac to factory.py Michel Aractingi 2024-12-23 14:12:03 +01:00
  • b53d6e0ff2 [HIL-SERL PORT] Fix linter issues (#588) Eugene Mironov 2024-12-23 16:44:29 +07:00
  • 70b652f791 [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
  • 73b64c3089 [vizualizer] for LeRobodDataset V2 (#576) Mishig 2024-12-20 16:26:23 +01:00
  • 7b68bfb73b added comments from kewang Michel Aractingi 2024-12-17 18:03:46 +01:00
  • 7e0f20fbf2 Enhance SAC configuration and policy with new parameters and subsampling logic KeWang1017 2024-12-17 15:58:04 +00:00
  • def42ff487 Port SAC WIP (#581) KeWang 2024-12-17 13:26:17 +00:00
  • c9af8e36a7 completed losses Michel Aractingi 2024-12-12 11:45:30 +01:00