Commit Graph

775 Commits

Author SHA1 Message Date
Cadene fc4b98544b Add tests to Readme 2024-02-25 10:52:31 +00:00
Cadene 6f5c731936 Rename test -> tests 2024-02-25 10:51:07 +00:00
Cadene 598bb496b0 Add policies/factory, Add test, Add _self_ in config 2024-02-25 10:50:23 +00:00
Cadene 64b5920e94 format 2024-02-24 18:19:18 +00:00
Cadene aed02dc7c6 Add multithreading for video generation, Speed policy sampling 2024-02-24 18:18:39 +00:00
Cadene 591985c67d Fix done in pusht, Fix --time in sbatch 2024-02-22 17:58:26 +00:00
Cadene 664cfb2023 Add sbatch.sh 2024-02-22 13:04:32 +00:00
Cadene 63d18475cc fix simxarm factory 2024-02-22 13:04:24 +00:00
Cadene 96c53ad06f remove comments 2024-02-22 12:15:14 +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 3dc14b5576 Add Prod transform, Add test_factory 2024-02-20 14:22:16 +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 fdfb2010fd black 2024-02-18 01:24:19 +00:00
Cadene a5c305a7a4 offline training + online finetuning converge to 33 reward! 2024-02-18 01:23:44 +00:00
Cadene 0b4084f0f8 Clean + alpha beta corresponds to config (before 0.7 and 0.9) 2024-02-16 16:27:54 +00:00
Cadene 0cdd23dcac Update README 2024-02-16 15:14:59 +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 937b2f8cba Add option for random policy 2024-01-31 13:54:32 +00:00
Cadene 5a5b190f70 Add common, refactor eval with eval_policy 2024-01-31 13:48:12 +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
Cadene 0396980450 .gitignore 2024-01-29 12:49:06 +00:00
Cadene 007ffa898f first commit 2024-01-26 15:51:11 +00:00