Commit Graph

Select branches

Hide Pull Requests

discrete

distributed

main

uncertainty-regularization

vectorized_env

#1

#10

#29

#36

#46

#47

#48

#49

#55

#66

#67

#75

#77

#85

#86

Mono Color

• 97c1447199 minor updates to vectorization vectorized_env Nicklas Hansen 2025-05-21 16:06:45 -07:00
• a586d8f393 fix merge error Nicklas Hansen 2025-05-20 14:09:13 -07:00
• 6116eb3fa5 fix merge error Nicklas Hansen 2025-05-20 13:59:12 -07:00
• 491d367fc6 Merge branch 'vectorized_env' of github.com:nicklashansen/tdmpc2 into vectorized_env Nicklas Hansen 2025-05-20 13:44:41 -07:00
• 10f368f20d init Nicklas Hansen 2024-02-11 14:41:20 -08:00
• 829e329b3b init Nicklas Hansen 2024-02-11 14:41:20 -08:00
• 8bbc14ebab Fix: handle _action_masks buffer in single-task scenarios (#67) main Sue Hyun Park 2025-05-20 12:12:12 +09:00
• 7992fa193e update readme + dockerfile Nicklas Hansen 2025-05-13 14:51:16 -07:00
• 7ec6bc83a8 only instantiate termination pred head if episodic=true Nicklas Hansen 2025-05-02 16:51:24 -07:00
• 38b31a5d72 only instantiate termination pred head if episodic=true Nicklas Hansen 2025-05-02 16:24:02 -07:00
• 7942e9082b update readme + clean up Nicklas Hansen 2025-04-15 16:32:15 -07:00
• eece80123d full support for episodic rl Nicklas Hansen 2025-04-15 15:55:05 -07:00
• 38f853efc4 clean up Nicklas Hansen 2025-04-15 10:16:02 -07:00
• 62be41ab58 experimental changes to termination prediction Nicklas Hansen 2025-04-10 00:32:13 -07:00
• c95b755655 add walker2d Nicklas Hansen 2025-04-09 15:55:57 -07:00
• 81eb17068e QoL improvements to termination signal debugging Nicklas Hansen 2025-04-08 19:15:31 -07:00
• add30b5a74 merge main into branch + fix termination in td-targets Nicklas Hansen 2025-04-08 12:40:10 -07:00
• 0a914570dc fix multitask model api conversion Nicklas Hansen 2025-02-27 16:25:21 -08:00
• 55bde9745f update torchrl version Nicklas Hansen 2025-02-05 16:46:34 -08:00
• 5ced6dfeb4 auto-convert old checkpoints to new format Nicklas Hansen 2025-02-05 16:26:19 -08:00
• dddc226d25 partial fix to loading checkpoints Nicklas Hansen 2025-01-21 00:10:53 -08:00
• ae4238946f Conversion tools for state-dicts (#55) Vincent Moens 2025-01-20 23:49:36 +00:00
• a19f91c0b5 enable torch.compile for offline rl + rgb inputs Nicklas Hansen 2024-12-25 12:22:39 -08:00
• e452ca7539 factor pi outputs Nicklas Hansen 2024-12-25 12:08:07 -08:00
• db1865334e refactor pi outputs Nicklas Hansen 2024-12-25 12:02:33 -08:00
• 804f9b3949 refactor pi outputs Nicklas Hansen 2024-12-24 03:05:00 -08:00
• 66f8c21f58 cache buffer values in offline training Nicklas Hansen 2024-12-19 09:40:04 -08:00
• 9cac7c5775 faster offline data loading Nicklas Hansen 2024-12-19 06:52:31 -08:00
• df8a465c8e update offline trainer to use new torch.load api Nicklas Hansen 2024-12-10 16:30:05 -08:00
• 2e27fbb6f4 partial fix for loading old checkpoints Nicklas Hansen 2024-12-10 16:04:27 -08:00
• 6117bc427d simplify dmcontrol wrappers + upgrade to gymnasium==0.29.1 Nicklas Hansen 2024-12-10 15:16:34 -08:00
• 32fc2bdf93 refactor policy Nicklas Hansen 2024-12-03 12:22:02 -08:00
• 5e276e6aaa Merge remote-tracking branch 'origin/main' into discrete discrete Nicklas Hansen 2024-11-28 12:02:22 -08:00
• 0a79c8bd38 update Dockerfile + environment.yaml Nicklas Hansen 2024-11-28 11:35:15 -08:00
• 4f07f1ced4 clean up discrete planning Nicklas Hansen 2024-11-24 16:47:02 -08:00
• 4dcd933b8f maximum entropy discrete policy Nicklas Hansen 2024-11-22 22:51:47 -08:00
• d463268bd2 update readme Nicklas Hansen 2024-11-12 13:46:04 -08:00
• 88ad0620ca add discrete planning Nicklas Hansen 2024-11-12 00:13:08 -08:00
• 8280b82d5c argmax policy works Nicklas Hansen 2024-11-11 22:36:40 -08:00
• a9b5ad0ff8 cleanup Nicklas Hansen 2024-11-11 19:09:09 -08:00
• dc6720d322 fix Nicklas Hansen 2024-11-11 18:20:09 -08:00
• dee034070e init Nicklas Hansen 2024-11-11 18:13:24 -08:00
• 10a0be2724 fix indexing Nicklas Hansen 2024-11-10 23:16:32 -08:00
• ad2342e258 Merge branch 'vectorized_env' of github.com:nicklashansen/tdmpc2 into vectorized_env Nicklas Hansen 2024-11-10 13:04:54 -08:00
• fa41a3e450 init Nicklas Hansen 2024-02-11 14:41:20 -08:00
• 1bfbcb7794 Merge pull request #49 from nicklashansen/speedups Nicklas Hansen 2024-11-10 12:33:32 -08:00
• 0c3fcc4619 update readme Nicklas Hansen 2024-11-10 12:32:57 -08:00
• fb07cdac3f update compile print Nicklas Hansen 2024-11-10 12:27:24 -08:00
• c694d286f0 add assertion for compile=true compatibility Nicklas Hansen 2024-11-10 12:25:43 -08:00
• 1a77207646 support newest version of myosuite Nicklas Hansen 2024-11-04 15:15:40 -08:00
• b7725e74a5 move cfg conversion to parser.py Nicklas Hansen 2024-10-31 14:52:59 -07:00
• d477619f8d Merge branch 'speedups' of github.com:nicklashansen/tdmpc2 into speedups Nicklas Hansen 2024-10-27 14:24:39 -07:00
• c1dd0c0338 minor QoL improvements in offline pipeline Nicklas Hansen 2024-10-27 14:24:19 -07:00
• c0d3faac77 Merge pull request #48 from vmoens/patch-1 Nicklas Hansen 2024-10-27 14:22:51 -07:00
• 3b5f67592c Update offline_trainer.py Vincent Moens 2024-10-26 00:33:27 +01:00
• fad0d1be03 Use torch.compiler.cudagraph_mark_step_begin() in eval Vincent Moens 2024-10-26 00:32:16 +01:00
• 836547d76f fix eval index + clean up Nicklas Hansen 2024-10-21 14:49:21 -07:00
• 970792e2b6 clean up prints Nicklas Hansen 2024-10-18 15:31:25 -07:00
• c3a912e10d Merge pull request #46 from vmoens/cudagraphs Nicklas Hansen 2024-10-18 09:35:33 -07:00
• 38eb46df04 Merge branch 'cudagraphs' of https://github.com/vmoens/tdmpc2 into cudagraphs Nicklas Hansen 2024-10-17 14:57:32 -07:00
• 8b731819a6 merged commits vmoens 2024-09-25 07:57:26 -07:00
• a7890b6985 add more results Nicklas Hansen 2024-10-06 21:11:38 -07:00
• 603b67ce66 merged commits vmoens 2024-09-25 07:57:26 -07:00
• 88095e7899 add more results Nicklas Hansen 2024-08-30 11:28:02 -07:00
• 4c03df676c update pinned torchrl version uncertainty-regularization Nicklas Hansen 2024-03-27 12:51:40 -07:00
• 8c299529a8 Update README.md Nicklas Hansen 2024-01-24 21:43:20 -08:00
• e96d4ae1a6 reduce # wandb calls Nicklas Hansen 2024-02-02 15:56:54 -08:00
• d28b03b3f9 update dockerfile Nicklas Hansen 2024-01-22 17:37:31 -08:00
• 614122644d update dockerfile + pin all versions Nicklas Hansen 2024-01-21 21:21:44 -08:00
• dc39c23067 minor fix in print Nicklas Hansen 2024-01-11 18:19:08 -08:00
• 173131ca48 migrate to slicebuffer from torchrl-nightly Nicklas Hansen 2024-01-10 19:53:30 -08:00
• 3789fcd5b8 update pinned torchrl version Nicklas Hansen 2024-03-27 12:51:40 -07:00
• d51feb0e9f Update README.md Nicklas Hansen 2024-01-24 21:43:20 -08:00
• 2dc668ecaf reduce # wandb calls Nicklas Hansen 2024-02-02 15:56:54 -08:00
• 39be86fc52 update dockerfile Nicklas Hansen 2024-01-22 17:37:31 -08:00
• f0af4b6b27 update dockerfile + pin all versions Nicklas Hansen 2024-01-21 21:21:44 -08:00
• a2d9d0c8ff minor fix in print Nicklas Hansen 2024-01-11 18:19:08 -08:00
• ab43880945 migrate to slicebuffer from torchrl-nightly Nicklas Hansen 2024-01-10 19:53:30 -08:00
• f6d1bfe12d update pinned torchrl version Nicklas Hansen 2024-03-27 12:51:40 -07:00
• b1afbccb05 update pinned torchrl version distributed Nicklas Hansen 2024-03-27 12:51:40 -07:00
• 5f6fadec0f update pinned torchrl version Nicklas Hansen 2024-03-27 12:51:40 -07:00
• c218c0ff1b update order of arch,params print Nicklas Hansen 2024-02-27 13:18:45 -08:00
• d3bff48d58 Merge branch 'distributed' of github.com:nicklashansen/tdmpc2 into distributed Nicklas Hansen 2024-02-27 13:18:18 -08:00
• c16f2557bb support distributed training Nicklas Hansen 2024-01-07 11:52:53 -08:00
• de87519c60 support distributed training Nicklas Hansen 2024-01-07 11:52:53 -08:00
• 9dd3e673c4 clean up Nicklas Hansen 2024-02-11 14:44:16 -08:00
• 51d6b8d7a9 init Nicklas Hansen 2024-02-11 14:41:20 -08:00
• 57158282b4 Merge branch 'main' of github.com:nicklashansen/tdmpc2 into main Nicklas Hansen 2024-02-02 15:56:56 -08:00
• 718966c28d reduce # wandb calls Nicklas Hansen 2024-02-02 15:56:54 -08:00
• 01cdf0f799 Update README.md Nicklas Hansen 2024-01-24 21:43:20 -08:00
• 02b18a48b1 update dockerfile Nicklas Hansen 2024-01-22 17:37:31 -08:00
• e8f1ed6785 update dockerfile + pin all versions Nicklas Hansen 2024-01-21 21:21:44 -08:00
• 8b6fe61bed minor fix in print Nicklas Hansen 2024-01-11 18:19:08 -08:00
• aa9c6f33f5 migrate to slicebuffer from torchrl-nightly Nicklas Hansen 2024-01-10 19:53:30 -08:00
• ff02f41e73 fix Nicklas Hansen 2024-01-08 17:18:22 -08:00
• 594299d7d1 Merge branch 'uncertainty-regularization' of github.com:nicklashansen/tdmpc2 into uncertainty-regularization Nicklas Hansen 2024-01-08 11:00:17 -08:00
• 188bd201aa disable uncertainty estimation when coef=0 Nicklas Hansen 2024-01-04 19:39:44 -08:00
• 392b16ac89 add uncertainty regularization Nicklas Hansen 2024-01-03 18:11:32 -08:00
• e86c343a67 Merge branch 'episodic-rl' of github.com:nicklashansen/tdmpc2 into episodic-rl Nicklas Hansen 2024-01-08 10:55:10 -08:00
• cc62c4c9ce init Nicklas Hansen 2024-01-07 18:16:33 -08:00