提交图

173 次代码提交

作者 SHA1 备注 提交日期
ef4bd9e25c Use dataclass config for ACT 2024-04-15 09:39:23 +01:00
c1a618e567 fix pusht images type from float32 to uint8, update gym-pusht dependencies 2024-04-11 14:29:16 +00:00
4216636084 fix 2024-04-11 14:01:23 +00:00
2f4af32d3f small fix 2024-04-11 13:21:06 +00:00
36de77ac18 fix and clarify tests 2024-04-11 13:16:47 +00:00
92701088a3 small fix 2024-04-11 13:04:27 +00:00
657b27cc8f fix load_data_with_delta_timestamps and add tests 2024-04-11 13:00:09 +00:00
9874652c2f enable test_compute_stats
enable test_compute_stats
2024-04-10 17:12:54 +00:00
ec4bf115d0 fix example_1 test 2024-04-10 13:55:59 +00:00
6082a7bc73 Enable test_available.py 2024-04-10 13:06:48 +00:00
7f4ff0b170 CI fix attempt 2024-04-09 11:58:59 +02:00
d21543eb4f Add env.close() 2024-04-09 10:41:20 +02:00
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
1149894e1d rename handle -> task 2024-04-08 14:54:52 +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
44656d2706 test_envs are passing 2024-04-05 23:27:12 +00:00
29032fbcd3 wrap dm_control aloha into gymnasium (TODO: properly seeding the env) 2024-04-05 17:17:14 +00:00
26602269cd test_envs.py are passing, remove simxarm and pusht directories 2024-04-05 16:21:07 +00:00
ab3cd3a7ba (WIP) Add gym-xarm 2024-04-05 15:35:20 +02:00
5af00d0c1e fix train.py, stats, eval.py (training is running) 2024-04-05 09:31:39 +00:00
c93ce35d8c WIP stats (TODO: run tests on stats + cmpute them) 2024-04-04 16:36:03 +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
a6ec4fbf58 remove try-catch 2024-04-03 09:53:15 +01:00
e9eb262293 numerically sound mean computation 2024-04-03 09:44:20 +01:00
7242953197 revision 2024-04-02 19:19:13 +01:00
c3234adc7d fix indentation 2024-04-02 16:59:19 +01:00
148df1c1d5 add comment on test 2024-04-02 16:57:25 +01:00
a6edb85da4 Remove random sampling 2024-04-02 16:52:38 +01:00
95293d459d fix stats computation 2024-04-02 16:40:33 +01:00
f1148b8c2d Merge remote-tracking branch 'upstream/main' into finish_examples 2024-04-01 11:31:31 +01:00
17c2bbbeb8 remove todo 2024-03-28 10:35:11 +01:00
6bddcb647e Add test_aloha env test 2024-03-28 10:35:11 +01:00
b7c9c33072 revision 2024-03-27 18:33:48 +00:00
be4441c7ff update README 2024-03-26 16:28:16 +00:00
1ed0110900 finish examples 2 and 3 2024-03-26 16:13:40 +00:00
9ced0cf1fb unskip 2024-03-26 10:45:31 +00:00
98534d1a63 skip 2024-03-26 10:42:53 +00:00
5a46b8a2a9 fix tests 2024-03-26 10:24:46 +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
058ac991eb Add simxarm back into tests 2024-03-25 16:35:46 +01:00
1c24bbda3f WIP Upgrading simxam from mujoco-py to mujoco python bindings 2024-03-25 12:28:07 +01:00
40f3783fca v1.2 2024-03-23 11:41:56 +00:00
f23a53c3e4 update stats.pth 2024-03-20 17:36:13 +00:00
d16f6a93b3 Merge remote-tracking branch 'upstream/main' into user/alexander-soare/multistep_policy_and_serial_env 2024-03-20 09:01:45 +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