4bafbe9009
Merge remote-tracking branch 'upstream/alexander-soare/qol_patches_for_eval' into refactor_tdmpc
2024-04-19 11:33:37 +01:00
09f26a8fbc
Merge remote-tracking branch 'upstream/main' into qol_patches_for_eval
2024-04-19 11:09:29 +01:00
2fa693e93b
Quality of life patches for eval.py
2024-04-19 11:06:29 +01:00
7ad1909641
Tests cleaning & simplification ( #81 )
2024-04-18 14:47:42 +02:00
0928afd37d
Improve dataset examples ( #82 )
...
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-04-18 11:43:16 +02:00
478284cce2
Merge remote-tracking branch 'upstream/main' into refactor_tdmpc
2024-04-18 10:17:02 +01:00
36d9e885ef
Address comments
2024-04-16 17:20:54 +00:00
e09d25267e
fix online training
2024-04-16 17:20:53 +00:00
67d79732f9
Add download_and_upload_dataset.py in script, update all datasets, update online training
2024-04-16 17:19:39 +00:00
9241b5e830
pass step as kwarg
2024-04-15 09:52:54 +01:00
949f4d1a5b
remove comment
2024-04-10 17:21:36 +00:00
4c3d8b061e
Update lerobot/scripts/eval.py
...
Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com>
2024-04-10 18:07:27 +02:00
8866b22db1
remove policy is None eval end-to-end tests
2024-04-10 15:09:04 +00:00
48ec479660
fix end-to-end aloha
2024-04-10 14:26:30 +00:00
a18bcb39a7
cfg.env.fps
2024-04-10 14:02:11 +00:00
7c8eb7ff19
Merge remote-tracking branch 'origin/user/rcadene/2024_03_31_remove_torchrl' into user/rcadene/2024_03_31_remove_torchrl
2024-04-10 11:34:51 +00:00
06573d7f67
online training works (loss goes down), remove repeat_action, eval_policy outputs episodes data, eval_policy uses max_episodes_rendered
2024-04-10 11:34:01 +00:00
6e14b85747
backup wip
2024-04-10 11:28:44 +01:00
e6c6c2367f
Merge remote-tracking branch 'upstream/user/rcadene/2024_03_31_remove_torchrl' into refactor_act
2024-04-09 08:36:28 +01:00
253e495df2
remove render(mode=visualization)
2024-04-09 03:46:05 +00:00
91e0e4e175
rever change
2024-04-08 15:05:40 +01:00
863f28ffd8
ready for review
2024-04-08 13:10:19 +01:00
1bab4a1dd5
Eval reproduction works with gym_aloha
2024-04-08 10:23:26 +01:00
8d2463f45b
backup wip
2024-04-05 18:46:30 +01:00
26602269cd
test_envs.py are passing, remove simxarm and pusht directories
2024-04-05 16:21:07 +00:00
5af00d0c1e
fix train.py, stats, eval.py (training is running)
2024-04-05 09:31:39 +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
6cd671040f
fix revision
2024-03-27 13:22:14 +00:00
1ed0110900
finish examples 2 and 3
2024-03-26 16:13:40 +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
7cdd6d2450
Renamed set_seed -> set_global_seed
2024-03-25 17:19:28 +01:00
bd40ffc53c
revision
2024-03-22 15:43:45 +00:00
d43fa600a0
only try to start env if it is closed
2024-03-22 15:32:55 +00:00
e698d38a35
Merge remote-tracking branch 'upstream/main' into fix_environment_seeding
2024-03-22 15:11:15 +00:00
15ff3b3af8
add fixes for reproducibility
2024-03-22 15:06:57 +00:00
115927d0f6
make sure to pass stats.pth arg
2024-03-22 12:58:59 +00:00
529f42643d
revision
2024-03-22 12:33:25 +00:00
8720c568d0
Add ability to eval hub model
2024-03-22 10:26:55 +00:00
4631d36c05
Add get_safe_torch_device in policies
2024-03-20 18:38:55 +01:00
5332766a82
revision
2024-03-20 09:45:45 +00:00
b1ec3da035
remove internal rendering hooks
2024-03-20 09:23:23 +00:00
52e149fbfd
Only save video frames in first rollout
2024-03-20 08:32:11 +00:00
4f1955edfd
Clear action queue when environment is reset
2024-03-20 08:31:06 +00:00
b54cdc9a0f
break_when_any_done==True for batch_size==1
2024-03-19 19:08:25 +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
09ddd9bf92
Merge branch 'main' into user/alexander-soare/multistep_policy_and_serial_env
2024-03-18 18:27:50 +00:00
8e346b379d
switch between train and eval
2024-03-18 09:45:17 +00:00
Alexander Soare
Simon Alibert
Remi
Simon Alibert