Releases | Open Source Science

stable-learning-control - v6.0.1

Full Changelog: https://github.com/rickstaa/stable-learning-control/compare/v6.0.0...v6.0.1

- Python
Published by rickstaa over 1 year ago

stable-learning-control - v6.0.0

6.0.0 (2024-03-15)

⚠ BREAKING CHANGES

buffers: the ReplayBuffer and TrajectoryBuffer classes don't take a rew_dim argument anymore.
package: The package should now be used as stable_learning_control instead of bayesian_learning_control.
This package now depends on Gymnasium instead of Gym. Furthermore, it also requires Gymnasium>=26 (see https://gymnasium.farama.org/content/migration-guide/) for more information.
The simzoo package is no longer included and has to be installed separately through the stable-gym repository.

Features

add docker container (#379) (972079f)
add hyperparameter variant support for exp config files (6ea47f0)
add small policy test script (c701d69)
add support for dictionary type observation spaces (e3bf761)
add torch reproducibility code (#320) (89ef5a2)
enable GPU device selection (#406) (73c1374)
exp_cfg: fix 'start_policy' empty config bug (e7f3cf9)
exp: add lambda lr check experiments (fedfa16)
exp: add min statistics to rstaa2024 data analysis (16ff564)
exp: add rstaa 2024 data analysis script (f0df0a4)
exp: rename CompOscillator lambda experiment (ec7103c)
improve 'eval_robustness' utility (#313) (3985867)
improve hyperparmeter tuning, logger and add W&B logging (#314) (74afd65)
lac: add finite-horizon Lyapunov Candidate (#328) (ed2c85d)
lac: implement Han et al. 2020 hyperparameters (#399) (574b651)
latc: add LATC algorithm (#323) (d74c64f)
package: renames the package to stable-learning-control (#257) (1133d0a)
plot: improve plotter arguments (#425) (c7202a2)
pytorch: add alpha/lambda learning rate customization (#412) (6feb749)
replace OpenAi gym with Gymnasium (#255) (9873a03)
tf2: add alpha/lambda learning rate customization (#416) (712e94b)
wandb: add 'wandbrunname' argument (#325) (e0a0b9d)

Bug Fixes

Address flake8 and black formatting issues (#395) (517ee30)
correct finite horizon buffer calculation (#398) (779201c)
correctly close gymnasium environments (#340) (a179176)
ensure 'test_policy' works with gymnasium>=0.28.1 (#276) (80fe370)
fix 'test_policy' episode length bug (#292) (6d34f74)
fix 'test_policy' rendering (#291) (48443ca)
fix environment validation (#280) (a8a0346)
fix plot dataframe loading (#338) (90e16e9)
fix several env/policy load bugs (dddd4d8)
fix several policy loading problems (51a664e)
improve tensorflow lazy import (#272) (75192a4)
pytorch: correct epoch-based learning rate decay behavior (#410) (a8df90f)
pytorch: correct step-based learning rate decay (#405) (7d7ac76)
pytorch: ensure correct application of constant learning rate (#411) (2b3693e)
pytorch: fix learning rate decay defaults (#414) (27964fe)
pytorch: resolve critical action rescaling bug (#403) (71d4f64)
remove 'simzoo' submodule (#246) (0122aae)
Resolve ruamel safe_load deprecation issue (#396) (cfcf81c)
run: resolve issue with data_dir input argument (#409) (8d93610)
tf2: correct off-by-one error in learning rate decay calculation (#415) (6ab5001)
tf2: correct step-based learning rate decay (#407) (642a193)
tf2: fix critical tf2 gradient update bug (#322) (dfc239b)
torch: handle 'update_after' set to zero (#408) (7999590)
wandb: fix wandb config format and run name (#317) (ca048de)

Documentation

add docker ownership admonition (58a8e70)
add policy test utility to docker page (5d39316)
add pre-commit note (#341) (9853d05)
add ros-gazebo-gym positive reward comment (#349) (9f5c434)
add snapshots comment to CONTRIBUTING (c2031b2)
add zenodo reference information (#300) (7180fb3)
contributing: updates the contributing documentation (bac8787)
fix broken external links (51317c0)
fix contribution links (#245) (cccc5a7)
fix doc code highlights (#404) (99126f7)
fix documentation (#377) (c3b47c5)
fix documentation latex formulas (#383) (#385) (582568b)
fix incorrect package naming (#282) (5337841)
fix incorrect run command (43df73f)
fix links (#268) (21c5bcf)
fix SAC alg run command (#380) (cf0a7a3)
fix typos (30df6cb)
improve code API documentation (#306) (16d5e26)
improve docs (#344) (908fd78)
improve documentation and package.json (#331) (e9fb90e)
improve documentation defaults (be99008)
improve documentation urls and syntax (#346) (22037cb)
improve package description (#260) (eabfef3)
improve polyak description (#417) (2404a4e)
improve the documentation (#265) (829eb05)
incorporate Docker usage instructions (#401) (2ba8031)
sphinx: fixes documentation errors (38f2da0)
sphinx: updates documentation installation instructions (ddadeb6)
update admonitions to new GFM specs (ae7d3bc)
update contribution note (#316) (44a35af)
update docs make file (6eeb56e)
update documentation (7ceee46)
update documentation and docstrings (5548505)
update numpy intersphinx link (581333d)
update sandbox description (#329) (f60cc3b)
updates code guidelines documentation (4f96a46)
updates docs ci readme badge (074b369)

Code Refactoring

buffers: remove unused 'rew_dim' argument (#327) (a69a7f6)

- Python
Published by rickstaa almost 2 years ago

stable-learning-control - v5.1.1

5.1.1 (2024-01-23)

Documentation

fix documentation latex formulas (#383) (#385) (582568b)

- Python
Published by rickstaa about 2 years ago

stable-learning-control - v5.1.0

5.1.0 (2024-01-23)

Features

add docker container (#379) (972079f)

Documentation

fix documentation (#377) (c3b47c5)
fix SAC alg run command (#380) (cf0a7a3)

- Python
Published by rickstaa about 2 years ago

stable-learning-control - v5.0.5

5.0.5 (2023-08-31)

Documentation

add ros-gazebo-gym positive reward comment (#349) (9f5c434)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v5.0.4

5.0.4 (2023-08-31)

Documentation

improve documentation urls and syntax (#346) (22037cb)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v5.0.3

5.0.3 (2023-08-29)

Documentation

improve docs (#344) (908fd78)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v5.0.2

5.0.2 (2023-08-28)

Bug Fixes

correctly close gymnasium environments (#340) (a179176)
fix plot dataframe loading (#338) (90e16e9)

Documentation

add pre-commit note (#341) (9853d05)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v5.0.1

5.0.1 (2023-08-14)

Documentation

improve documentation and package.json (#331) (e9fb90e)
update sandbox description (#329) (f60cc3b)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v5.0.0

5.0.0 (2023-08-12)

⚠ BREAKING CHANGES

buffers: the ReplayBuffer and TrajectoryBuffer classes don't take a rew_dim argument anymore.

Features

lac: add finite-horizon Lyapunov Candidate (#328) (ed2c85d)
wandb: add 'wandbrunname' argument (#325) (e0a0b9d)

Code Refactoring

buffers: remove unused 'rew_dim' argument (#327) (a69a7f6)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.3.0

4.3.0 (2023-08-11)

Features

add torch reproducibility code (#320) (89ef5a2)
latc: add LATC algorithm (#323) (d74c64f)

Bug Fixes

tf2: fix critical tf2 gradient update bug (#322) (dfc239b)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.2.0

4.2.0 (2023-08-08)

Features

improve hyperparmeter tuning, logger and add W&B logging (#314) (74afd65)

Bug Fixes

wandb: fix wandb config format and run name (#317) (ca048de)

Documentation

update contribution note (#316) (44a35af)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.1.0

4.1.0 (2023-08-02)

Features

improve 'eval_robustness' utility (#313) (3985867)

Documentation

update admonitions to new GFM specs (ae7d3bc)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.10

4.0.10 (2023-07-15)

Documentation

improve code API documentation (#306) (16d5e26)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.9

4.0.9 (2023-07-11)

Documentation

add zenodo reference information (#300) (7180fb3)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.8

4.0.8 (2023-07-10)

Documentation

add snapshots comment to CONTRIBUTING (c2031b2)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.7

4.0.7 (2023-07-09)

Bug Fixes

fix 'test_policy' episode length bug (#292) (6d34f74)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.6

4.0.6 (2023-07-09)

Bug Fixes

fix 'test_policy' rendering (#291) (48443ca)

Documentation

improve documentation defaults (be99008)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.5

4.0.5 (2023-07-06)

Bug Fixes

ensure 'test_policy' works with gymnasium>=0.28.1 (#276) (80fe370)
fix environment validation (#280) (a8a0346)

Documentation

fix incorrect package naming (#282) (5337841)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.4

4.0.4 (2023-07-01)

Bug Fixes

improve tensorflow lazy import (#272) (75192a4)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.3

4.0.3 (2023-06-29)

Documentation

fix links (#268) (21c5bcf)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.2

4.0.2 (2023-06-29)

Documentation

improve the documentation (#265) (829eb05)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.1

4.0.1 (2023-06-22)

Documentation

improve package description (#260) (eabfef3)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v4.0.0

4.0.0 (2023-06-22)

⚠ BREAKING CHANGES

package: The package should now be used as stable_learning_control instead of bayesian_learning_control.
This package now depends on Gymnasium instead of Gym. Furthermore, it also requires Gymnasium>=26 (see https://gymnasium.farama.org/content/migration-guide/) for more information.

Features

package: renames the package to stable-learning-control (#257) (1133d0a)
replace OpenAi gym with Gymnasium (#255) (9873a03)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v3.0.0

3.0.0 (2023-06-21)

⚠ BREAKING CHANGES

The simzoo package is no longer included and has to be installed separately through the stable-gym repository.

Features

add hyperparameter variant support for exp config files (6ea47f0)
add small policy test script (c701d69)
add support for dictionary type observation spaces (e3bf761)

Bug Fixes

fix several env/policy load bugs (dddd4d8)
fix several policy loading problems (51a664e)
fixes npm release action (e47ef0f)
package.json: this commit makes sure the release run script contains no bugs (ef958ca)
remove 'simzoo' submodule (#246) (0122aae)

Documentation

contributing: updates contributing guide (ce126c4)
contributing: updates the contributing documentation (bac8787)
fix broken external links (51317c0)
fix contribution links (#245) (cccc5a7)
fix typos (30df6cb)
readme.md: adds contributing warning to readme (d848a14)
sphinx: fixes documentation errors (38f2da0)
sphinx: updates documentation installation instructions (ddadeb6)
update docs make file (6eeb56e)
update documentation (7ceee46)
update documentation and docstrings (5548505)
update numpy intersphinx link (581333d)
updates code guidelines documentation (4f96a46)
updates docs ci readme badge (074b369)

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v2.0.0

2.0.0 (2023-06-21)

⚠ BREAKING CHANGES

The simzoo package is no longer included and has to be installed separately through the stable-gym repository.

Features

add hyperparameter variant support for exp config files (6ea47f0)
add small policy test script (c701d69)
add support for dictionary type observation spaces (e3bf761)

Bug Fixes

fix several env/policy load bugs (dddd4d8)
fix several policy loading problems (51a664e)
fixes npm release action (e47ef0f)
package.json: this commit makes sure the release run script contains no bugs (ef958ca)
remove 'simzoo' submodule (#246) (0122aae)

- Python
Published by rickstaa over 2 years ago

stable-learning-control -

- Python
Published by rickstaa over 2 years ago

stable-learning-control - v1.3.13

🔄 Dependency updates

chore(deps): update dependency lint-staged to v12.4.0
- PR: #184

Uncategorized

- Python
Published by github-actions[bot] almost 4 years ago

stable-learning-control - v1.3.12

🔄 Dependency updates

chore(deps): update dependency sort-package-json to v1.55.0
- PR: #182

Uncategorized

- Python
Published by github-actions[bot] almost 4 years ago

stable-learning-control - v1.3.10

🔄 Dependency updates

chore(deps): pin dependency standard-version to 9.3.2
- PR: #180

Uncategorized

- Python
Published by github-actions[bot] almost 4 years ago