Commit Graph

322 Commits

Author SHA1 Message Date
Cadene 70aaf1c4cb test_datasets.py are passing! 2024-04-08 14:16:57 +00:00
Cadene e1ac5dc62f fix aloha pixels env test 2024-04-07 17:20:54 +00:00
Cadene 4371a5570d Remove latency, tdmpc policy passes tests (TODO: make it work with online RL) 2024-04-07 16:01:22 +00:00
Cadene 44656d2706 test_envs are passing 2024-04-05 23:27:12 +00:00
Cadene 5eff40b3d6 rename task, sim_transfer -> transfer 2024-04-05 17:18:37 +00:00
Cadene a2d3588fca wrap dm_control aloha into gymnasium (TODO: properly seeding the env) 2024-04-05 17:17:31 +00:00
Cadene 29032fbcd3 wrap dm_control aloha into gymnasium (TODO: properly seeding the env) 2024-04-05 17:17:14 +00:00
Cadene 26602269cd test_envs.py are passing, remove simxarm and pusht directories 2024-04-05 16:21:07 +00:00
Cadene f56b1a0e16 WIP tdmpc 2024-04-05 13:40:31 +00:00
Simon Alibert ab3cd3a7ba (WIP) Add gym-xarm 2024-04-05 15:35:20 +02:00
Cadene c17dffe944 policies/utils.py 2024-04-05 11:47:15 +00:00
Cadene a420714ee4 fix: action_is_pad was missing in compute_loss 2024-04-05 11:33:39 +00:00
Cadene ad3379a73a fix memory leak due to itertools.cycle 2024-04-05 10:59:32 +00:00
Cadene 5af00d0c1e fix train.py, stats, eval.py (training is running) 2024-04-05 09:31:39 +00:00
Cadene c93ce35d8c WIP stats (TODO: run tests on stats + cmpute them) 2024-04-04 16:36:03 +00:00
Cadene 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
Alexander Soare 920e0d118b
Merge pull request #66 from alexander-soare/fix_stats_computation
fix stats computation
2024-04-03 10:03:47 +01:00
Alexander Soare caf4ffcf65 add TODO 2024-04-03 09:56:46 +01:00
Alexander Soare a6ec4fbf58 remove try-catch 2024-04-03 09:53:15 +01:00
Alexander Soare c50a62dd6d clarifying math 2024-04-03 09:47:38 +01:00
Alexander Soare e9eb262293 numerically sound mean computation 2024-04-03 09:44:20 +01:00
Alexander Soare 7242953197 revision 2024-04-02 19:19:13 +01:00
Alexander Soare c3234adc7d fix indentation 2024-04-02 16:59:19 +01:00
Alexander Soare 148df1c1d5 add comment on test 2024-04-02 16:57:25 +01:00
Alexander Soare a6edb85da4 Remove random sampling 2024-04-02 16:52:38 +01:00
Alexander Soare 95293d459d fix stats computation 2024-04-02 16:40:33 +01:00
Alexander Soare 11cbf1bea1
Merge pull request #53 from alexander-soare/finish_examples
Add examples 2 and 3
2024-04-01 11:52:41 +01:00
Alexander Soare f1148b8c2d Merge remote-tracking branch 'upstream/main' into finish_examples 2024-04-01 11:31:31 +01:00
Simon Alibert 2a98cc71ed
Merge pull request #56 from huggingface/user/aliberts/2024_03_27_improve_ci
Add code coverage, more end-to-end tests
2024-03-28 10:57:44 +01:00
Simon Alibert a7c9b78e56 Deactivate eval ACT on Aloha (policy is None) 2024-03-28 10:55:11 +01:00
Simon Alibert 404b8f8a75 Fix end-to-end ACT train on Aloha 2024-03-28 10:35:11 +01:00
Simon Alibert 17c2bbbeb8 remove todo 2024-03-28 10:35:11 +01:00
Simon Alibert 006e5feabf WIP add code coverage 2024-03-28 10:35:11 +01:00
Simon Alibert b99ee8180a Add more end-to-end tests 2024-03-28 10:35:11 +01:00
Simon Alibert 6bddcb647e Add test_aloha env test 2024-03-28 10:35:11 +01:00
Simon Alibert 58df2066a9 Add pytest-cov 2024-03-28 10:35:11 +01:00
Simon Alibert c89aa4f8ed
Merge pull request #57 from huggingface/user/aliberts/2024_03_27_improve_readme
Improve readme
2024-03-28 10:26:48 +01:00
Simon Alibert 62aad7104b Pull merge 2024-03-28 10:03:25 +01:00
Simon Alibert 9d9148dad8 Fixes for #57 2024-03-28 10:01:33 +01:00
Simon Alibert 1b6cb2b1be
Add space
Co-authored-by: Remi <re.cadene@gmail.com>
2024-03-27 20:51:52 +01:00
Simon Alibert 6f1a0aefab
typo fix
Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
2024-03-27 20:50:23 +01:00
Alexander Soare b7c9c33072 revision 2024-03-27 18:33:48 +00:00
Alexander Soare 120f0aef5c Merge remote-tracking branch 'upstream/main' into finish_examples 2024-03-27 17:52:36 +00:00
Simon Alibert 032200e32c Typo fix 2024-03-27 17:05:04 +01:00
Simon Alibert de1e9187c8 Formatting 2024-03-27 16:56:21 +01:00
Simon Alibert 4f8f1926f9 Update pip install without requirements.txt 2024-03-27 16:49:27 +01:00
Simon Alibert 6710121a29 Revert "Add requirements.txt"
This reverts commit 18e7f4c3e6.
2024-03-27 16:47:49 +01:00
Simon Alibert 5f4b8ab899 Add more exhaustive install instructions 2024-03-27 16:35:32 +01:00
Simon Alibert 18e7f4c3e6 Add requirements.txt 2024-03-27 16:33:54 +01:00
Simon Alibert 643d64e2a8 Add cmake 2024-03-27 16:33:26 +01:00