Commit Graph

103 Commits

Author SHA1 Message Date
Nicklas Hansen
38eb46df04 Merge branch 'cudagraphs' of https://github.com/vmoens/tdmpc2 into cudagraphs 2024-10-17 14:57:32 -07:00
vmoens
8b731819a6 merged commits 2024-10-08 10:24:02 -07:00
Nicklas Hansen
a7890b6985 add more results 2024-10-06 21:11:38 -07:00
vmoens
603b67ce66 merged commits 2024-10-03 16:09:48 +01:00
Nicklas Hansen
88095e7899 add more results 2024-08-30 11:28:02 -07:00
Nicklas Hansen
3789fcd5b8 update pinned torchrl version 2024-07-02 10:12:06 -07:00
Nicklas Hansen
d51feb0e9f Update README.md 2024-07-02 10:12:06 -07:00
Nicklas Hansen
2dc668ecaf reduce # wandb calls 2024-07-02 10:12:06 -07:00
Nicklas Hansen
39be86fc52 update dockerfile 2024-07-02 10:12:06 -07:00
Nicklas Hansen
f0af4b6b27 update dockerfile + pin all versions 2024-07-02 10:12:06 -07:00
Nicklas Hansen
a2d9d0c8ff minor fix in print 2024-07-02 10:12:06 -07:00
Nicklas Hansen
ab43880945 migrate to slicebuffer from torchrl-nightly 2024-07-02 10:12:06 -07:00
Nicklas Hansen
f6d1bfe12d update pinned torchrl version 2024-07-02 10:11:13 -07:00
Nicklas Hansen
5f6fadec0f update pinned torchrl version 2024-03-27 12:51:40 -07:00
Nicklas Hansen
9dd3e673c4 clean up 2024-02-11 14:44:16 -08:00
Nicklas Hansen
51d6b8d7a9 init 2024-02-11 14:41:20 -08:00
Nicklas Hansen
57158282b4 Merge branch 'main' of github.com:nicklashansen/tdmpc2 into main 2024-02-02 15:56:56 -08:00
Nicklas Hansen
718966c28d reduce # wandb calls 2024-02-02 15:56:54 -08:00
Nicklas Hansen
01cdf0f799 Update README.md 2024-01-24 21:43:20 -08:00
Nicklas Hansen
02b18a48b1 update dockerfile 2024-01-22 17:37:31 -08:00
Nicklas Hansen
e8f1ed6785 update dockerfile + pin all versions 2024-01-21 21:21:44 -08:00
Nicklas Hansen
8b6fe61bed minor fix in print 2024-01-11 18:19:08 -08:00
Nicklas Hansen
aa9c6f33f5 migrate to slicebuffer from torchrl-nightly 2024-01-10 19:53:30 -08:00
Nicklas Hansen
ff02f41e73 fix 2024-01-08 17:18:22 -08:00
Nicklas Hansen
e86c343a67 Merge branch 'episodic-rl' of github.com:nicklashansen/tdmpc2 into episodic-rl 2024-01-08 10:55:10 -08:00
Nicklas Hansen
cc62c4c9ce init 2024-01-08 10:51:27 -08:00
Nicklas Hansen
0f3bc77011 amend slicesampler indexing 2024-01-08 10:48:04 -08:00
Nicklas Hansen
fabf01a5ec solves episodic variant of cartpole-balance-sparse 2024-01-07 19:28:41 -08:00
Nicklas Hansen
26c72119cd init 2024-01-07 18:16:33 -08:00
Nicklas Hansen
31249a8961 separate episodes with nans 2024-01-07 14:21:38 -08:00
Nicklas Hansen
33876d124f add instructions for distributed training 2024-01-07 11:55:07 -08:00
Nicklas Hansen
a7ff00b0cd add option to disable planning with mpc=false 2024-01-04 19:17:47 -08:00
Nicklas Hansen
13cac07759 fix minor logging issue in offline trainer 2024-01-03 10:12:28 -08:00
Nicklas Hansen
1d224cec3a update documentation 2023-12-31 14:38:22 -08:00
Nicklas Hansen
e3c876670a add launcher 2023-12-29 16:37:26 -08:00
Nicklas Hansen
1f6c7771b9 Merge pull request #10 from nicklashansen/experimental
[Feature] Faster replay buffer + support pixel observations
2023-12-28 16:37:27 +01:00
Nicklas Hansen
6cb779aa3a allow missing env dependencies + update readme 2023-12-28 07:33:03 -08:00
Nicklas Hansen
54145a4d8c integrate slicesampler as default 2023-12-27 08:49:04 -08:00
Nicklas Hansen
2f86a1e4d8 fix sampler https://github.com/pytorch/rl/pull/1762 2023-12-25 10:11:42 -08:00
Nicklas Hansen
ca4dfa1db3 further reduce buffer differences 2023-12-23 09:39:13 -08:00
Nicklas Hansen
eef1d1b407 unit test buffer implementations 2023-12-23 07:43:28 -08:00
Nicklas Hansen
70fe242adc does not reproduce results w/ previous buffer 2023-12-22 14:26:48 -08:00
Nicklas Hansen
2929cfdb44 fix computation of mem requirements 2023-12-22 13:57:01 -08:00
Nicklas Hansen
34ea3662cd compare new/old buffers 2023-12-22 13:34:12 -08:00
Nicklas Hansen
fea0936e69 set logging defaults 2023-12-22 07:44:34 -08:00
Nicklas Hansen
95bf14e343 Merge branch 'main' of github.com:nicklashansen/tdmpc2 into experimental 2023-12-22 07:43:44 -08:00
Nicklas Hansen
bfb1971898 naive support for pixels 2023-12-22 07:34:40 -08:00
Nicklas Hansen
3ded0ebc83 faster replay buffer implementation 2023-12-22 05:55:43 -08:00
Nicklas Hansen
445af9d81d easier customization of architecture:
all args can now be set freely when model_size is not specified
2023-12-06 08:15:54 -08:00
Nicklas Hansen
f3139291e2 update dependencies 2023-11-25 19:20:52 -08:00