daa1480a91
nit
2025-01-22 10:26:52 +01:00
71ec721e48
cleaned eval_on_robot.py; readded policy; fixed doc strings
2025-01-22 10:26:52 +01:00
bbb5ba0adf
Extend reward classifier for multiple camera views ( #626 )
2025-01-22 10:26:52 +01:00
844bfcf484
[Port HIL_SERL] Final fixes for the Reward Classifier ( #598 )
2025-01-22 10:26:52 +01:00
13441f0d98
added temporary fix for missing task_index key in online environment
2025-01-22 10:26:50 +01:00
41b377211c
split encoder for critic and actor
2025-01-22 10:25:52 +01:00
9ceb68ee90
Refine SAC configuration and policy for enhanced performance
...
- Updated standard deviation parameterization in SACConfig to 'softplus' with defined min and max values for improved stability.
- Modified action sampling in SACPolicy to use reparameterized sampling, ensuring better gradient flow and log probability calculations.
- Cleaned up log probability calculations in TanhMultivariateNormalDiag for clarity and efficiency.
- Increased evaluation frequency in YAML configuration to 50000 for more efficient training cycles.
These changes aim to enhance the robustness and performance of the SAC implementation during training and inference.
2025-01-22 10:23:33 +01:00
d1baa5a82f
trying to get sac running
2025-01-22 10:20:56 +01:00
04da4dd3e3
Added normalization schemes and style checks
2025-01-22 10:19:19 +01:00
b0e2fcdba7
added optimizer and sac to factory.py
2025-01-22 10:17:48 +01:00
1e2a757cd3
[Port Hil-SERL] Add unit tests for the reward classifier & fix imports & check script ( #578 )
2025-01-22 10:14:06 +01:00
ab842ba6ae
nit in control_robot.py
2025-01-22 10:06:39 +01:00
94a7221a94
Update lerobot/scripts/train_hilserl_classifier.py
...
Co-authored-by: Yoel <yoel.chornton@gmail.com>
2025-01-22 10:06:39 +01:00
00dadcace0
LerobotDataset pushable to HF from any folder ( #563 )
2025-01-22 10:06:39 +01:00
81a2f2958d
Update 7_get_started_with_real_robot.md ( #559 )
2025-01-22 10:06:39 +01:00
68b4fb60ad
Control simulated robot with real leader ( #514 )
...
Co-authored-by: Remi <remi.cadene@huggingface.co>
2025-01-22 10:06:39 +01:00
96b2b62377
Fix missing local_files_only in record/replay ( #540 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
2025-01-22 10:06:39 +01:00
b5c98bbfd3
Refactor OpenX ( #505 )
2025-01-22 10:06:39 +01:00
58e12cf2e8
Fixup
2025-01-22 10:06:39 +01:00
d8b5fae622
Add human intervention mechanism and eval_robot script to evaluate policy on the robot ( #541 )
...
Co-authored-by: Yoel <yoel.chornton@gmail.com>
2025-01-22 10:06:39 +01:00
67ac81d728
Reward classifier and training ( #528 )
...
Co-authored-by: Daniel Ritchie <daniel@brainwavecollective.ai>
Co-authored-by: resolver101757 <kelster101757@hotmail.com>
Co-authored-by: Jannik Grothusen <56967823+J4nn1K@users.noreply.github.com>
Co-authored-by: Remi <re.cadene@gmail.com>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
2025-01-22 10:06:39 +01:00
b5f1ea3140
nit
2025-01-22 10:06:39 +01:00
4d854a1513
Stable version of rlpd + drq
2025-01-22 09:00:16 +00:00
87da655eab
Add type annotations and restructure SACConfig class fields
2025-01-21 09:51:12 +00:00
a8fda9c61a
Change SAC policy implementation with configuration and modeling classes
2025-01-17 09:39:04 +01:00
55505ff817
Add rlpd tricks
2025-01-16 11:53:36 +01:00
20d31ab8e0
SAC works
2025-01-16 11:53:27 +01:00
e5b83aab5e
remove breakpoint
2025-01-16 11:52:03 +01:00
a9d5f62304
[WIP] correct sac implementation
2025-01-16 11:51:18 +01:00
72e1ed7058
Add rlpd tricks
2025-01-16 11:42:24 +01:00
d8e67a2609
SAC works
2025-01-16 11:42:24 +01:00
50e12376de
remove breakpoint
2025-01-16 11:42:23 +01:00
73aa6c25f3
[WIP] correct sac implementation
2025-01-16 11:42:14 +01:00
380b836eee
Fix for the issue https://github.com/huggingface/lerobot/issues/638 ( #639 )
2025-01-15 10:50:38 +01:00
eec6796cb8
fixes to SO-100 readme ( #600 )
...
Co-authored-by: Philip Fung <no@one>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-01-10 11:30:01 +01:00
25a8597680
[viz] Fixes & updates to html visualizer ( #617 )
2025-01-09 11:39:54 +01:00
b8b368310c
typo fix: batch_convert_dataset_v1_to_v2.py ( #615 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-01-09 09:57:45 +01:00
5097cd900e
fix(visualise): use correct language description for each episode id ( #604 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-01-09 09:39:48 +01:00
bc16e1b497
fix(docs): typos in benchmark readme.md ( #614 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-01-09 09:35:27 +01:00
8f821ecad0
Fix Quality workflow ( #622 )
2025-01-08 13:35:11 +01:00
4519016e67
Update README.md ( #612 )
2025-01-03 16:19:37 +01:00
59e2757434
Fix broken `create_lerobot_dataset_card` ( #590 )
2024-12-23 15:05:59 +01:00
73b64c3089
[vizualizer] for LeRobodDataset V2 ( #576 )
2024-12-20 16:26:23 +01:00
66f8736598
fixing typo from 'teloperation' to 'teleoperation' ( #566 )
2024-12-11 05:57:52 -08:00
4c41f6fcc6
Fix example 6 ( #572 )
2024-12-11 10:32:18 +01:00
44f9b21e74
LerobotDataset pushable to HF from any folder ( #563 )
2024-12-09 11:32:25 +01:00
03f49ceaf0
Update 7_get_started_with_real_robot.md ( #559 )
2024-12-09 00:17:49 +01:00
8e7d6970ea
Control simulated robot with real leader ( #514 )
...
Co-authored-by: Remi <remi.cadene@huggingface.co>
2024-12-03 12:20:05 +01:00
286bca37cc
Fix missing local_files_only in record/replay ( #540 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
2024-12-03 10:53:21 +01:00
a2c181992a
Refactor OpenX ( #505 )
2024-12-03 00:51:55 +01:00
Michel Aractingi
Eugene Mironov
KeWang1017
Claudio Coppola
berjaoui
Remi
Yoel
AdilZouitine
Pradeep Kadubandi
Philip Fung
Mishig
CharlesCNorton
Ville Kuosmanen
Simon Alibert
s1lent4gnt