dodox/metastable-baselines
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Commit Graph

  • 4854346f2d Fixed bug with logging of std for full-cov dodox 2022-07-16 14:58:00 +02:00
  • cb9ee4f302 Fixed bugs for Hybrid[Diag=>Full] dodox 2022-07-16 14:57:34 +02:00
  • ad584d70fd Removed debugging prints dodox 2022-07-16 13:07:08 +02:00
  • 72754525cd Allow using newly implemented hybrid method dodox 2022-07-16 13:06:07 +02:00
  • fa167b3e5f Hybrid Diag -> Full Implemented; Made spherical_chol more efficient dodox 2022-07-16 13:05:35 +02:00
  • f184b88f19 Allow std logging for full and diagonal cov policies dodox 2022-07-15 18:46:42 +02:00
  • 74697e8773 Smol bug fixes dodox 2022-07-15 18:46:17 +02:00
  • 2e0f46b0f3 Fixing ser/deser bug (cloudpickle cant handle some enums) dodox 2022-07-15 18:45:38 +02:00
  • a86d19053d Smashing bugs (dimension mismatch between Normal and Independent/MultivariateNormal) dodox 2022-07-15 15:46:31 +02:00
  • ab557a8856 Making MultivariateNormal Policies work (and porting Normal to Independent) dodox 2022-07-15 15:03:51 +02:00
  • b1ed9fc2b8 Renamed TRL_PG to PPO dodox 2022-07-13 19:51:33 +02:00
  • 1706bea571 Testing SDC dodox 2022-07-13 19:39:09 +02:00
  • 3304fd49f6 Working on UniversalGaussianDistribution dodox 2022-07-13 19:38:57 +02:00
  • fae19509bc Implemented Policies with Contextual Covariance dodox 2022-07-13 19:38:20 +02:00
  • 41e4170b2f Fixes + spherical_chol dodox 2022-07-11 17:28:08 +02:00
  • e4440428f8 Working on SDC dodox 2022-07-11 11:55:23 +02:00
  • 4c4b12ee0e Allow cloning UniversalGaussianDistribution (new_dist_like) dodox 2022-07-09 14:45:35 +02:00
  • c08ea1cb91 Making UniversalGaussianDistribution ready for tanh-squashing-support dodox 2022-07-09 14:33:07 +02:00
  • 249754ee89 Wrote a little helper-function to generate all allowed combinations of cov-parameterizations dodox 2022-07-09 14:03:56 +02:00
  • e09950b30c Work on Contextual Covariances dodox 2022-07-09 12:26:39 +02:00
  • aacacebfc4 Fixed license dodox 2022-07-06 13:26:33 +02:00
  • 0911a04e98 Factored out Gaussian Collection for RolloutBuffer dodox 2022-07-04 21:21:16 +02:00
  • 1f3eac5398 Cleanup dodox 2022-07-02 16:42:14 +02:00
  • 92204c448f Testing kl-projection (it's working!) dodox 2022-07-02 16:41:25 +02:00
  • ad7ed0071b Silence! dodox 2022-07-01 20:02:29 +02:00
  • 91f64c10d7 Fixed bug with initialization of buffer dodox 2022-07-01 20:02:09 +02:00
  • 0dc9edf112 We no longer use venv (breaks cpp_projection...) dodox 2022-07-01 19:52:22 +02:00
  • 14100cccc8 Working on SDC-impl. dodox 2022-07-01 15:14:41 +02:00
  • 4f2e75b7ae Slimmed 3rd-party-licenses dodox 2022-07-01 14:03:50 +02:00
  • 90b3c68a56 Maybe better licensing dodox 2022-07-01 13:59:07 +02:00
  • cc51547681 Fixed CppProjection in requirements dodox 2022-07-01 13:47:04 +02:00
  • 84d1cda96c Trying to get kl to work dodox 2022-07-01 13:45:58 +02:00
  • 9d7ce73a0b README: We also have to install cpp_projection dodox 2022-07-01 12:30:29 +02:00
  • 111b1b846d Now we even include a setup.py dodox 2022-07-01 12:22:27 +02:00
  • 81ae3e3707 Finalized venv support and added installation-instructions dodox 2022-07-01 12:19:57 +02:00
  • f25d7a103b Now ready to pvenv dodox 2022-07-01 12:03:20 +02:00
  • 2626ec82a6 Added code-src-note dodox 2022-07-01 11:52:50 +02:00
  • ab1b269af9 Allow checking whether a dist is contextual dodox 2022-07-01 11:52:14 +02:00
  • a8b9c63965 Making dez covariances contextual dodox 2022-07-01 11:29:12 +02:00
  • 155a298e41 Switching to new icon dodox 2022-06-30 21:02:22 +02:00
  • 7e7ba65e51 Testing alternative icon dodox 2022-06-30 21:01:25 +02:00
  • 2e378d0a7d Rebranding to Metastable Baselines dodox 2022-06-30 20:40:30 +02:00
  • 30c9e93967 Fixed replay dodox 2022-06-29 17:02:40 +02:00
  • 28561b9bb2 Allow manual early stopping of training (Ctrl+C) dodox 2022-06-29 12:46:57 +02:00
  • e8d423f91f Testing the new WassersteinProjectionLayer dodox 2022-06-29 12:46:37 +02:00
  • 4e77190d8e Fixed chol not expanding bug and function to shrink chol to diag dodox 2022-06-29 12:44:13 +02:00
  • 7c117cfca5 Added possibility to load models and run hem again (currently bugged) dodox 2022-06-29 12:43:21 +02:00
  • 416dde202d Factored out frob_sq and perf improvement for spd input dodox 2022-06-27 13:44:08 +02:00
  • f4c87c9cdc Better handling of diagonal-covariance as vector and matrix dodox 2022-06-26 18:14:12 +02:00
  • bc61a6db32 Refactored some stuff out dodox 2022-06-26 16:39:37 +02:00
  • edf00553dd Renamed our RolloutBuffer and testing the FrobeniusProjectionLayer dodox 2022-06-26 16:39:06 +02:00
  • 024a9a0265 StillTesting dodox 2022-06-26 16:38:46 +02:00
  • 80741776d2 Removed old comments dodox 2022-06-25 21:56:07 +02:00
  • b8488c531b Implemented TRLRolloutBuffer dodox 2022-06-25 21:47:39 +02:00
  • 60c954c8c1 LunarLanderContinuous-v2 is our new default test-env dodox 2022-06-25 21:47:21 +02:00
  • cf5a2e82fc mean and std are now saved to the rollout dodox 2022-06-25 18:29:55 +02:00
  • df21e1dc3f Fixed reference to gym.spaces dodox 2022-06-25 17:49:46 +02:00
  • 5f7cfd2e10 Note about Code-Src dodox 2022-06-25 15:37:45 +02:00
  • b9f66dd95d Using BaseProjectionLayer as Default dodox 2022-06-25 15:33:43 +02:00
  • cafc90409f _global_steps ctr added dodox 2022-06-25 15:05:54 +02:00
  • 866f863d70 overriding collect_rollouts dodox 2022-06-25 14:57:27 +02:00
  • 1a49a412c0 expanding automatic testing dodox 2022-06-25 14:50:19 +02:00
  • 25316ec0b8 Incremental progress at implementing trl_pg dodox 2022-06-25 13:58:58 +02:00
  • 941b7347f1 Get FPS from env dodox 2022-06-22 13:12:55 +02:00
  • 0e17b4c07e Fixed model storage location bug dodox 2022-06-22 13:00:40 +02:00
  • 41d4e94dbe Extended .gitignore dodox 2022-06-22 13:00:28 +02:00
  • 84b3710850 Testing SACs ability to solve EasierObstacles-v0 dodox 2022-06-21 15:15:38 +02:00
  • 13d335f856 models added to .gitignore dodox 2022-06-21 15:15:22 +02:00
  • e71735bf79 Trying to converge on simple columbus envs dodox 2022-06-20 23:12:42 +02:00
  • b9303416ac Split PPO_SDE into PPO_BASE_SDE and PPO_LATENT_SDE dodox 2022-06-19 22:47:04 +02:00
  • c0a5b6650d Added model*.py to .gitignore dodox 2022-06-19 20:34:33 +02:00
  • 477a3c48b1 Testing the RayObserver dodox 2022-06-19 20:34:04 +02:00
  • 605a81c81c No longer needing update_subtrees.sh dodox 2022-06-19 16:30:46 +02:00
  • 7b8f2e7109 I dont like subtrees dodox 2022-06-19 16:30:32 +02:00
  • 12e9e09add Updating Columbus - Merge commit '132176985464f6ba2e8f7c88794215644f7f9066' dodox 2022-06-19 16:15:58 +02:00
  • 1321769854 Squashed 'subtrees/columbus/' changes from 489a098..6ebd95e dodox 2022-06-19 16:15:58 +02:00
  • 26ba8c64c7 Update Columbus - Merge commit 'a49eae378dc65a73e101cd094703ebd80534de77' dodox 2022-06-19 16:07:12 +02:00
  • a49eae378d Squashed 'subtrees/columbus/' changes from abad4bd..489a098 dodox 2022-06-19 16:07:12 +02:00
  • e2724734cf Updating Columbus - Merge commit 'de5f6e2f810d08b043ea02cdaf59d380fe23288c' dodox 2022-06-19 16:00:13 +02:00
  • de5f6e2f81 Squashed 'subtrees/columbus/' changes from 57d8068..abad4bd dodox 2022-06-19 16:00:13 +02:00
  • c45e3627ea Trying to get ColumbusEnv to work... dodox 2022-06-19 15:59:55 +02:00
  • f950d1fe64 Update Columbus - Merge commit 'c8ec2f71e88386bc822797dbe97af04d8ad4bb8d' dodox 2022-06-19 15:54:40 +02:00
  • c8ec2f71e8 Squashed 'subtrees/columbus/' changes from 279b4d9..57d8068 dodox 2022-06-19 15:54:40 +02:00
  • 9707ed0149 Update Columbus - Merge commit '00954032000c2229edfd645d4131b27e716da2f9' dodox 2022-06-19 15:52:56 +02:00
  • 0095403200 Squashed 'subtrees/columbus/' changes from daf8ec2..279b4d9 dodox 2022-06-19 15:52:56 +02:00
  • 9ca6ad9afc Update Columbus - Merge commit '46f742c1ee05a7a81685a330fc5fd0777f281563' dodox 2022-06-19 15:51:55 +02:00
  • 46f742c1ee Squashed 'subtrees/columbus/' changes from 12cac4d..daf8ec2 dodox 2022-06-19 15:51:55 +02:00
  • 04d74e3d6a Made update_subtrees.sh executable dodox 2022-06-19 15:51:43 +02:00
  • 0721aa2a85 Added update_subtrees.sh to automate updating dependencies dodox 2022-06-19 15:51:09 +02:00
  • fcc33d7bdc Work on Columbus integration dodox 2022-06-19 15:50:54 +02:00
  • 1a21bb9ad4 Merge commit 'fd6edb02f716fa7d40468101797de231adc20c00' as 'subtrees/columbus' dodox 2022-06-19 15:46:03 +02:00
  • fd6edb02f7 Squashed 'subtrees/columbus/' content from commit 12cac4d dodox 2022-06-19 15:46:03 +02:00
  • 50c83db6e5 No pyc-files dodox 2022-06-17 15:59:43 +02:00
  • 6789a41730 Merge branch 'master' of dominik.roth.ml:dodox/sb3_trl dodox 2022-06-17 15:58:53 +02:00
  • bb160d2837 changed locations / names for logs dodox 2022-06-17 13:16:32 +02:00
  • dd5e3e94b7 changed locations / names for logs dodox 2022-06-17 13:16:32 +02:00
  • 2190d68826 pyc in .gitignore dodox 2022-06-17 12:27:39 +02:00
  • d8d67468a7 pyc in .gitignore dodox 2022-06-17 12:27:39 +02:00
  • e363021ed3 Removed old files (moved into sb3_trl/) dodox 2022-06-17 11:31:25 +02:00
  • c90805fdff Removed old files (moved into sb3_trl/) dodox 2022-06-17 11:31:25 +02:00