tangger/lerobot_piper
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
183 Commits 2 Branches 0 Tags
c5010fee9a40c64d61e69918ee64691f69a4b4c8
Commit Graph

47 Commits

Author SHA1 Message Date
Alexander Soare
896a11f60e backup wip 2024-03-19 18:50:04 +00:00
Alexander Soare
ea17f4ce50 backup wip 2024-03-19 16:02:09 +00:00
Alexander Soare
88347965c2 revert dp changes, make act and tdmpc batch friendly 2024-03-18 19:18:21 +00:00
Alexander Soare
bae7e7b41c Merge remote-tracking branch 'origin/main' into user/alexander-soare/multistep_policy_and_serial_env 2024-03-15 14:06:53 +00:00
Alexander Soare
4ecfd17f9e fix wandb artifact name and add disable option 2024-03-15 13:56:55 +00:00
Alexander Soare
a222c88c99 Merge branch 'user/alexander-soare/train_pusht' into user/alexander-soare/multistep_policy_and_serial_env 2024-03-14 16:06:21 +00:00
Alexander Soare
ba91976944 wip: still needs batch logic for act and tdmp 2024-03-14 15:24:10 +00:00
Alexander Soare
98484ac68e ready for review 2024-03-12 21:59:01 +00:00
Alexander Soare
9512d1d2f3 Merge branch 'main' into user/alexander-soare/train_pusht 2024-03-12 19:41:27 +00:00
Remi Cadene
9d002032d1 Add Aloha env and ACT policy 
WIP Aloha env tests pass

Rendering works (fps look fast tho? TODO action bounding is too wide [-1,1])

Update README

Copy past from act repo

Remove download.py add a WIP for Simxarm

Remove download.py add a WIP for Simxarm

Add act yaml (TODO: try train.py)

Training can runs (TODO: eval)

Add tasks without end_effector that are compatible with dataset, Eval can run (TODO: training and pretrained model)

Add AbstractEnv, Refactor AlohaEnv, Add rendering_hook in env, Minor modifications, (TODO: Refactor Pusht and Simxarm)

poetry lock

fix bug in compute_stats for action normalization

fix more bugs in normalization

fix training

fix import

PushtEnv inheriates AbstractEnv, Improve factory Normalization

Add _make_env to EnvAbstract

Add call_rendering_hooks to pusht env

SimxarmEnv inherites from AbstractEnv (NOT TESTED)

Add aloha tests artifacts + update pusht stats

fix image normalization: before env was in [0,1] but dataset in [0,255], and now both in [0,255]

Small fix on simxarm

Add next to obs

Add top camera to Aloha env (TODO: make it compatible with set of cameras)

Add top camera to Aloha env (TODO: make it compatible with set of cameras)
 2024-03-12 10:27:48 +00:00
Alexander Soare
87fcc536f9 wip - still need to verify full training run 2024-03-11 18:45:21 +00:00
Alexander Soare
304355c917 Merge remote-tracking branch 'origin/main' into train_pusht 2024-03-11 15:37:37 +00:00
Alexander Soare
2a01487494 early training loss as expected 2024-03-11 13:34:04 +00:00
Simon Alibert
6d6c84b4a3 Remove entity from config 
Co-authored-by: Remi <re.cadene@gmail.com>
 2024-03-11 14:14:17 +01:00
Simon Alibert
00fe4f4f18 Configure wandb entity outside config 2024-03-11 13:09:46 +01:00
Simon Alibert
6c867d78ef Integrate pusht env from diffusion 2024-03-10 16:33:03 +01:00
Remi Cadene
d782b029e1 Add aloha dataset 2024-03-06 10:26:32 +00:00
Remi Cadene
e132a267aa offline_prioritized_sampler: true 2024-03-04 23:17:59 +00:00
Remi Cadene
a027f4edfb Add cfg.offline_prioritized_sampler 2024-03-04 23:08:52 +00:00
Remi
e990f3e148 Merge pull request #6 from Cadene/user/rcadene/2024_03_04_diffusion 
Make diffusion work
 2024-03-04 18:30:40 +01:00
Remi Cadene
e29fbb50e8 Fix grad_clip_norm 0 -> 10, Fix normalization min_max to be per channel 2024-03-04 17:26:34 +00:00
Remi Cadene
cfc304e870 Refactor env queue, Training diffusion works (Still not converging) 2024-03-04 11:00:51 +00:00
Remi Cadene
0f2fa4d9ef Add obs queue to pusht, Set n_obs_steps=2 for diffusion (Not fully tested) 2024-03-03 13:21:31 +00:00
Simon Alibert
b33ec5a630 Add run on cpu-only compatibility 2024-03-03 12:47:26 +01:00
Remi Cadene
661bda45ea imagenet_norm: False 2024-03-02 17:18:58 +00:00
Cadene
0b9027f05e Clean logging, Refactor 2024-02-29 23:21:27 +00:00
Simon Alibert
7e024fdce6 Ran pre-commit run --all-files 2024-02-29 13:37:48 +01:00
Cadene
ac90b9c3ee Fix diffusion (rm transpose), Add prefetch 2024-02-28 17:45:01 +00:00
Cadene
cf5063e50e Add diffusion policy (train and eval works, TODO: reproduce results) 2024-02-28 15:21:42 +00:00
Simon Alibert
f1708c8a37 install fix 2024-02-28 12:35:49 +01:00
Cadene
7df542445c Small fix and improve logging message 2024-02-27 11:44:26 +00:00
Cadene
21670dce90 Refactor train, eval_policy, logger, Add diffusion.yaml (WIP) 2024-02-26 01:10:09 +00:00
Cadene
5a219fed6e Refactor policy config 2024-02-25 18:26:44 +00:00
Cadene
b16c334825 Refactor configs to have env in seperate yaml + Fix training 2024-02-25 17:42:47 +00:00
Cadene
eec134d72b small change 2024-02-25 14:20:14 +00:00
Cadene
ed80db2846 Sanitize cfg.env 2024-02-25 12:02:29 +00:00
Cadene
9b469c4232 Fix pusht.yaml 2024-02-25 11:49:39 +00:00
Cadene
0eb9b5d1a5 Sanitize cfg.wandb 2024-02-25 11:15:09 +00:00
Cadene
e765e26b0b Sanitize cfg.policy, Fix skip_frame pusht.yaml 2024-02-25 11:09:02 +00:00
Cadene
598bb496b0 Add policies/factory, Add test, Add _self_ in config 2024-02-25 10:50:23 +00:00
Cadene
e3643d6146 Wandb works, One output dir 2024-02-22 12:14:12 +00:00
Cadene
ece89730e6 Add pusht dataset (TODO verify reward is aligned), Refactor visualize_dataset, Add video_dir, fps, state_dim, action_dim to config (Training works) 2024-02-21 00:49:40 +00:00
Cadene
3da6ffb2cb Fix unit tests, Refactor, Add pusht env, (TODO pusht replay buffer, image preprocessing) 2024-02-20 12:26:57 +00:00
Cadene
c202c2b3c2 Online finetuning runs (sometimes crash because of nans) 2024-02-16 15:13:24 +00:00
Cadene
228c045674 Eval reproduced! Train running (but not reproduced) 2024-02-10 15:46:24 +00:00
Cadene
1e52499490 eval.mp4 works! 2024-01-30 23:30:14 +00:00
Cadene
1144819c29 First real commit, simxarm env added with torchrl! 2024-01-29 12:49:30 +00:00