|
|
9cd25ee484
|
Support passing trajectories into predictiion functions (for pca)
|
2023-05-21 20:16:25 +02:00 |
|
|
|
d4003e1a68
|
get_past_trajectories will now return a th.Tensor
|
2023-05-21 17:29:03 +02:00 |
|
|
|
ea7634ca42
|
Revert "typo: trajectory -> traj"
This reverts commit becb8d36e1.
|
2023-05-21 17:26:13 +02:00 |
|
|
|
becb8d36e1
|
typo: trajectory -> traj
|
2023-05-21 17:22:59 +02:00 |
|
|
|
69fdd7b103
|
Fix Bug: Let's let thge pca-lib handle this exception
|
2023-05-21 17:19:39 +02:00 |
|
|
|
c473990fbd
|
Fix smol Bug
|
2023-05-21 17:15:46 +02:00 |
|
|
|
834b5c9a65
|
Fixed Bug: Can not get past trajectory from rolloutBuffer
|
2023-05-21 17:11:32 +02:00 |
|
|
|
6a9d7012c7
|
Bugs
|
2023-05-21 17:03:22 +02:00 |
|
|
|
43418a5e53
|
Tiny Bugfix
|
2023-05-21 16:40:13 +02:00 |
|
|
|
a1df15f7bc
|
Fixed PCA bug
|
2023-05-21 16:32:27 +02:00 |
|
|
|
ea4b9851d8
|
Fixed: Binding to PCA used old package name
|
2023-05-21 16:23:51 +02:00 |
|
|
|
8921421732
|
Fixed Typo
|
2023-05-21 16:14:34 +02:00 |
|
|
|
2efa6c18fb
|
Experimental Support for PCA
|
2023-05-21 14:27:09 +02:00 |
|
|
|
76ea3a6326
|
Implemented prior conditioned annealing (untested)
|
2023-04-25 17:05:34 +02:00 |
|
|
|
09159774d9
|
Fix backward pass error for hybrid-method
|
2023-03-13 20:44:09 +01:00 |
|
|
|
75feefbe5a
|
Fix: Typos for sde/rex hybrid
|
2023-02-18 12:42:07 +01:00 |
|
|
|
c62723bef6
|
First implementation of hybrid (bewteen sde and rex)
|
2023-02-18 12:18:46 +01:00 |
|
|
|
ae9a95cbfc
|
Fix: Typo in SAC
|
2023-02-02 20:00:16 +01:00 |
|
|
|
71670782b6
|
.
|
2023-01-28 21:47:19 +01:00 |
|
|
|
b86498fa9a
|
Now softmax sde latent is actually working...
|
2023-01-28 19:48:43 +01:00 |
|
|
|
e985d892ca
|
New SDE feature: softmax activation of latent
|
2023-01-28 19:42:32 +01:00 |
|
|
|
ffbf2b3fe5
|
Allow reduced latent sde dim
|
2023-01-27 13:34:28 +01:00 |
|
|
|
f421dc2ab5
|
Removed hack again...
|
2023-01-26 18:18:38 +01:00 |
|
|
|
f86c6c736f
|
Hack is back
|
2023-01-26 18:15:06 +01:00 |
|
|
|
20646f07f3
|
Reverting last two commits (was ugly hack)
|
2023-01-26 17:43:57 +01:00 |
|
|
|
6f1837bda5
|
calc episodic infos for some fancy envs
|
2023-01-26 17:27:34 +01:00 |
|
|
|
f37c8caaa4
|
Force include reward in env infos (for vec env)
|
2023-01-26 12:00:18 +01:00 |
|
|
|
43cc749809
|
Fix Noise Reset Bug for SAC
|
2023-01-15 13:28:40 +01:00 |
|
|
|
844cdb1319
|
Fixed: Upgrade changing interfaces
|
2023-01-06 18:46:38 +01:00 |
|
|
|
f3e03916c8
|
Upgrading to SB3 1.7 (probably broke some stuff...)
|
2022-12-13 19:14:28 +01:00 |
|
|
|
c47d5741ca
|
New Version of SB3
|
2022-12-13 18:38:33 +01:00 |
|
|
|
9cb7e89b1d
|
MIT License
|
2022-11-13 20:07:08 +01:00 |
|
|
|
4ec5c65cf2
|
Tiny fix for other envs
|
2022-11-07 13:23:55 +01:00 |
|
|
|
302dbf6dde
|
Pruning of README 2nd try
|
2022-11-07 12:59:12 +01:00 |
|
|
|
c5ed794325
|
Updated requirements
|
2022-11-07 12:55:15 +01:00 |
|
|
|
d89609e276
|
Merge branch 'master' of dominik-roth.eu:dodox/metastable-baselines
|
2022-11-07 12:46:22 +01:00 |
|
|
|
479d73ac4b
|
Hotfix for exploding gradients
|
2022-11-03 20:13:36 +01:00 |
|
|
|
82a174122a
|
Fixed bugs with givens-rotator for eigen
|
2022-10-24 10:08:31 +02:00 |
|
|
|
e31c25135e
|
Fixed Bug with Givens Rotation (Eigen)
|
2022-10-09 11:24:06 +02:00 |
|
|
|
f9a08add40
|
Action-Loss for SAC
|
2022-10-08 18:33:37 +02:00 |
|
|
|
3110275d7b
|
Fixed bug with EIGEN (par_type)
|
2022-10-07 11:38:34 +02:00 |
|
|
|
f37d3215a6
|
Bug Fix for Full Cov
|
2022-09-23 23:06:19 +02:00 |
|
|
|
00dbc9bdd8
|
Error when calculating action_loss
|
2022-09-12 22:28:57 +02:00 |
|
|
|
2c14edd3b0
|
Fix: Dependency
|
2022-09-03 23:41:06 +02:00 |
|
|
|
d3fa3cc997
|
Fixed Givens Dependency
|
2022-09-03 23:16:54 +02:00 |
|
|
|
6e1a7cecd5
|
Implemented correct clipping (from original SAC)
|
2022-09-03 13:46:17 +02:00 |
|
|
|
ee4a0eed56
|
Fixed SAC+SDE+SDC bugs
|
2022-09-03 13:08:31 +02:00 |
|
|
|
4532135812
|
Finalized factoring out projections
|
2022-09-03 11:59:16 +02:00 |
|
|
|
0aeea4e2e5
|
Fixed Bug: Wrong dimensions for action_loss
|
2022-09-03 11:44:01 +02:00 |
|
|
|
4bb772a251
|
Factor Projections out into metastable-projections
|
2022-09-03 11:37:41 +02:00 |
|
