75dd478b54
Revert "Revert "Override action queue defaults""
...
This reverts commit 5647d71c08
2024-05-03 11:05:59 +02:00
5647d71c08
Revert "Override action queue defaults"
...
This reverts commit 7592c21eb2751c4ecc0fc1badb437f34b0f2155e.
2024-05-03 10:04:49 +02:00
61f38da7a3
Override action queue defaults
2024-05-03 10:04:49 +02:00
6f11b0afaf
Cleanup
2024-05-03 10:04:49 +02:00
1acfd61b88
Dial back to atol=1e-7
2024-05-03 10:04:49 +02:00
97ded04b07
Try atol=1e-8
2024-05-03 10:04:49 +02:00
82b5ffb250
Try rtol=0.1
2024-05-03 10:04:49 +02:00
90cb75acfd
atol=1e-7
2024-05-03 10:04:49 +02:00
590b0eb48f
Add require_x86_64_kernel
2024-05-03 10:04:49 +02:00
55ff23c252
rtol=0.5
2024-05-03 10:04:49 +02:00
2d11199320
rtol=1, atol=1e-6 for all asserts
2024-05-03 10:04:49 +02:00
8f54825b1f
rtol=1, atol=1e-6
2024-05-03 10:04:49 +02:00
8e842ac00c
rtol=1e-4, atol=1e-7
2024-05-03 10:04:49 +02:00
e75448c8c4
Generate artifacts from x86 cpu
2024-05-03 10:04:49 +02:00
2ca594e801
atol = 1e-3
2024-05-03 10:04:49 +02:00
ff2cc0d7b1
Increase tolerance further again
2024-05-03 10:04:49 +02:00
53ae422eb8
Increase tolerance further
2024-05-03 10:04:49 +02:00
c3e57c2ae7
Increase tolerance
2024-05-03 10:04:49 +02:00
77ee567851
Add require_cpu
2024-05-03 10:04:49 +02:00
344c1653f2
Fix device
2024-05-03 10:04:49 +02:00
326933f208
Remove require_cuda
2024-05-03 10:04:49 +02:00
3a918b980f
WIP
2024-05-03 10:04:48 +02:00
276d210380
Add require_cuda
2024-05-03 10:04:48 +02:00
c1ecfdc663
Move to test_policies
2024-05-03 10:04:48 +02:00
d1855a202a
Refactor TD-MPC ( #103 )
...
Co-authored-by: Cadene <re.cadene@gmail.com>
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-05-01 16:40:04 +01:00
a4891095e4
Use PytorchModelHubMixin to save models as safetensors ( #125 )
...
Co-authored-by: Remi <re.cadene@gmail.com>
2024-05-01 16:17:18 +01:00
01d5490d44
Follow `transformers` single file naming conventions ( #124 )
2024-05-01 13:09:42 +01:00
9d60dce6f3
Tidy up yaml configs ( #121 )
2024-04-30 16:08:59 +01:00
508bd92d03
Remove `update` method from the policy ( #99 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-29 12:27:58 +02:00
ccffa9e406
Fix policy defaults ( #113 )
2024-04-29 08:26:59 +01:00
659c69a1c0
Refactor datasets into LeRobotDataset ( #91 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-25 12:23:12 +02:00
e760e4cd63
Move normalization to policy for act and diffusion ( #90 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-25 11:47:38 +02:00
7ad1909641
Tests cleaning & simplification ( #81 )
2024-04-18 14:47:42 +02:00
8a322da422
backup wip
2024-04-16 16:35:04 +01:00
23be5e1e7b
backup wip
2024-04-16 16:31:44 +01:00
6902e01db0
tests are passing for aloha/act policies, removes abstract policy
2024-04-09 03:28:56 +00:00
73dfa3c8e3
tests for tdmpc and diffusion policy are passing
2024-04-09 02:50:32 +00:00
3f6dfa4916
Add gym-aloha, rename simxarm -> xarm, refactor
2024-04-08 16:24:11 +02:00
70aaf1c4cb
test_datasets.py are passing!
2024-04-08 14:16:57 +00:00
4371a5570d
Remove latency, tdmpc policy passes tests (TODO: make it work with online RL)
2024-04-07 16:01:22 +00:00
1cdfbc8b52
WIP
...
WIP
WIP train.py works, loss going down
WIP eval.py
Fix
WIP (eval running, TODO: verify results reproduced)
Eval works! (testing reproducibility)
WIP
pretrained model pusht reproduces same results as torchrl
pretrained model pusht reproduces same results as torchrl
Remove AbstractPolicy, Move all queues in select_action
WIP test_datasets passed (TODO: re-enable NormalizeTransform)
2024-04-04 15:31:03 +00:00
b7c9c33072
revision
2024-03-27 18:33:48 +00:00
1a1308d62f
fix environment seeding
...
add fixes for reproducibility
only try to start env if it is closed
revision
fix normalization and data type
Improve README
Improve README
Tests are passing, Eval pretrained model works, Add gif
Update gif
Update gif
Update gif
Update gif
Update README
Update README
update minor
Update README.md
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Update README.md
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
Address suggestions
Update thumbnail + stats
Update thumbnail + stats
Update README.md
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
Add more comments
Add test_examples.py
2024-03-26 10:10:43 +00:00
058ac991eb
Add simxarm back into tests
2024-03-25 16:35:46 +01:00
40f3783fca
v1.2
2024-03-23 11:41:56 +00:00
b54cdc9a0f
break_when_any_done==True for batch_size==1
2024-03-19 19:08:25 +00:00
46ac87d2a6
ready for review
2024-03-19 18:59:08 +00:00
896a11f60e
backup wip
2024-03-19 18:50:04 +00:00
ea17f4ce50
backup wip
2024-03-19 16:02:09 +00:00
88347965c2
revert dp changes, make act and tdmpc batch friendly
2024-03-18 19:18:21 +00:00
Simon Alibert
Alexander Soare
Quentin Gallouédec
Remi
Simon Alibert