6380f82bbc
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.
2025-03-24 13:24:23 +01:00
ecb91b37eb
Refactor SACPolicy for improved action sampling and standard deviation handling
...
- Updated action selection to use distribution sampling and log probabilities for better stochastic behavior.
- Enhanced standard deviation clamping to prevent extreme values, ensuring stability in policy outputs.
- Cleaned up code by removing unnecessary comments and improving readability.
These changes aim to refine the SAC implementation, enhancing its robustness and performance during training and inference.
2025-03-24 13:24:23 +01:00
c89bcc5aa8
trying to get sac running
2025-03-24 13:24:23 +01:00
cc85bca2b5
Added normalization schemes and style checks
2025-03-24 13:24:23 +01:00
3b07766c33
added optimizer and sac to factory.py
2025-03-24 13:23:53 +01:00
287968b418
[HIL-SERL PORT] Fix linter issues ( #588 )
2025-03-24 13:23:02 +01:00
c9f1a037e3
[Port Hil-SERL] Add unit tests for the reward classifier & fix imports & check script ( #578 )
2025-03-24 13:23:02 +01:00
8a7f74ee65
added comments from kewang
2025-03-24 13:21:05 +01:00
8220546036
Enhance SAC configuration and policy with new parameters and subsampling logic
...
- Added `num_subsample_critics`, `critic_target_update_weight`, and `utd_ratio` to SACConfig.
- Implemented target entropy calculation in SACPolicy if not provided.
- Introduced subsampling of critics to prevent overfitting during updates.
- Updated temperature loss calculation to use the new target entropy.
- Added comments for future UTD update implementation.
These changes improve the flexibility and performance of the SAC implementation.
2025-03-24 13:21:05 +01:00
214beec994
Port SAC WIP ( #581 )
...
Co-authored-by: KeWang1017 <ke.wang@helloleap.ai>
2025-03-24 13:21:05 +01:00
909ca8d9b6
completed losses
2025-03-24 13:21:05 +01:00
5fe56e0a49
nit in control_robot.py
2025-03-24 13:21:05 +01:00
a60d3facee
Update lerobot/scripts/train_hilserl_classifier.py
...
Co-authored-by: Yoel <yoel.chornton@gmail.com>
2025-03-24 13:21:04 +01:00
298a31bc45
LerobotDataset pushable to HF from any folder ( #563 )
2025-03-24 13:21:04 +01:00
05b8f8b4fd
Update 7_get_started_with_real_robot.md ( #559 )
2025-03-24 13:21:04 +01:00
0f05dc5faf
Control simulated robot with real leader ( #514 )
...
Co-authored-by: Remi <remi.cadene@huggingface.co>
2025-03-24 13:21:04 +01:00
36d89156b1
Fix missing local_files_only in record/replay ( #540 )
...
Co-authored-by: Simon Alibert <alibert.sim@gmail.com>
2025-03-24 13:21:04 +01:00
1dd5e3cd3f
Refactor OpenX ( #505 )
2025-03-24 13:21:04 +01:00
4f8633dd26
Fixup
2025-03-24 13:21:04 +01:00
d733e5681f
Add human intervention mechanism and eval_robot script to evaluate policy on the robot ( #541 )
...
Co-authored-by: Yoel <yoel.chornton@gmail.com>
2025-03-24 13:21:02 +01:00
0ebdae8a40
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>
2025-03-24 13:20:43 +01:00
d037f4a322
nit
2025-03-24 13:19:37 +01:00
a6015a55f9
chore(scripts): remove deprecated script ( #887 )
2025-03-23 01:16:50 +01:00
f39652707c
add docs details for resolving firmware update issues ( #627 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-03-19 19:17:07 +01:00
712d5dae4f
fix(os): fix default codec for windows ( #875 )
2025-03-18 22:04:21 +01:00
952e892fe5
Use float32 instead of int ( #877 )
2025-03-18 16:36:37 +01:00
e8159997c7
User/pepijn/2025 03 17 act different image shapes ( #870 )
2025-03-18 11:09:05 +01:00
1c15bab70f
fix(codec): hot-fix for default codec in linux arm platforms ( #868 )
2025-03-17 13:23:11 +01:00
9f0a8a49d0
Update test-docker-build.yml
2025-03-15 11:34:17 +01:00
a3cd18eda9
added wandb.run_id to allow resuming without wandb log; updated log m… ( #841 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-03-15 09:40:39 +01:00
7dc9ffe4c9
Update 10_use_so100.md ( #840 )
2025-03-14 17:07:14 +01:00
0e98c6ee96
Add torchcodec cpu ( #798 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Remi <re.cadene@gmail.com>
Co-authored-by: Remi <remi.cadene@huggingface.co>
Co-authored-by: Simon Alibert <simon.alibert@huggingface.co>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-03-14 16:53:42 +01:00
974028bd28
Organize test folders ( #856 )
...
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-03-13 14:05:55 +01:00
a36ed39487
Improve pre-commit config ( #857 )
2025-03-13 13:29:55 +01:00
c37b1d45b6
parametrise tolerance_s in visualize_dataset scripts ( #716 )
2025-03-13 10:28:29 +01:00
f994febca4
[pre-commit.ci] pre-commit autoupdate ( #844 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-03-11 11:28:01 +01:00
12f52632ed
chore(docs): update instructions for change in device and use_amp ( #843 )
2025-03-10 21:03:33 +01:00
8a64d8268b
chore(deps): remove hydra dependency ( #842 )
2025-03-10 19:00:23 +01:00
84565c7c2e
Fix camera rotation error ( #839 )
...
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-03-10 17:02:19 +01:00
05b54733da
feat: add support for external plugin config dataclasses ( #807 )
...
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-03-10 13:25:47 +01:00
513b008bcc
fix: deactivate tdmpc backward compatibility test with use_mpc=True ( #838 )
2025-03-10 10:19:54 +01:00
32fffd4bbb
Fix delay in teleoperation start time ( #676 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-03-08 11:40:07 +01:00
03c7cf8a63
Remove pr_style_bot ( #832 )
2025-03-08 09:39:07 +01:00
074f0ac8fe
Fix gpu nightly ( #829 )
2025-03-07 13:21:58 +01:00
25c63ccf63
🐛 Remove `map_location=device` that no longer exists when loading DiffusionPolicy from_pretained after commit 5e94738 ( #830 )
...
Co-authored-by: Mathias Wulfman <mathias.wulfman@wandercraft.eu>
2025-03-07 13:21:11 +01:00
5e9473806c
refactor(config): Move device & amp args to PreTrainedConfig ( #812 )
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2025-03-06 17:59:28 +01:00
10706ed753
Support for discrete actions ( #810 )
2025-03-06 10:27:29 +01:00
0b8205a8a0
chore(doc): add star history graph to the README.md ( #815 )
2025-03-06 09:44:21 +01:00
57ae509823
Revert "docs: update installation instructions to use uv instead of conda" ( #827 )
2025-03-06 09:43:27 +01:00
5d24ce3160
chore(doc): add license header to all files ( #818 )
2025-03-05 17:56:51 +01:00
KeWang1017
Michel Aractingi
Eugene Mironov
KeWang
Claudio Coppola
berjaoui
Remi
Yoel
Steven Palma
Cole
Pepijn
Guillaume LEGENDRE
Huan Liu
Jade Choghari
Simon Alibert
Ermano Arruda
pre-commit-ci[bot]
Ben Sprenger
Joe Clinton
Mathias Wulfman
Harsimrat Sandhawalia