A toolkit for reproducible reinforcement learning research.
This is a pre-release of v2020.10. It contains changes to garage since v2020.06.0.
This pre-release makes cutting-edge features available via PyPI, but comes with no promises of support or bug fixes. If you encounter problems with this release, you are encouraged to either install from master or revert to the v2020.06 release.
For information on what to expected in garage v2020.09, see the release notes for v2020.06.0
This is a maintenance release for 2020.06.
LocalRunner
ignores worker_cls
attribute of algorithms (#1984)mujoco_py
versions greater than v2.0.2.8 are incompatible with some GCC versions in conda (#2000)GarageEnv
twice (#2029)max_episode_length_eval
hyperparameter (#2029)max_episode_length
for evalaution via the max_episode_length_eval
hyperparameter (#2029)max_episode_length
(#2029)This is a pre-release of v2020.09. It contains changes to garage since v2020.06.0.
This pre-release makes cutting-edge features available via PyPI, but comes with no promises of support or bug fixes. If you encounter problems with this release, you are encouraged to either install from master or revert to the v2020.06 release.
For information on what to expected in garage v2020.09, see the release notes for v2020.06.0
This is a pre-release of v2020.09. It contains changes to garage since v2020.06.0.
This pre-release makes cutting-edge features available via PyPI, but comes with no promises of support or bug fixes. If you encounter problems with this release, you are encouraged to either install from master or revert to the v2020.06 release.
For information on what to expected in garage v2020.09, see the release notes for v2020.06.0
This is a pre-release of v2020.09. It contains changes to garage since v2020.06.0.
This pre-release makes cutting-edge features available via PyPI, but comes with no promises of support or bug fixes. If you encounter problems with this release, you are encouraged to either install from master or revert to the v2020.06 release.
For information on what to expected in garage v2020.09, see the release notes for v2020.06.0
This is a maintenance release for 2020.06.
her_ddpg_fetchreach
(#1763)tfp.SeedStream
(#1821)DiscreteQfDerivedPolicy
in which parameters were not returned (#1847)TimeLimit.truncated
at every step when using gym.Env
(#1852)clone()
ed (#1855)Makefile
target run-nvidia
(#1914)This is a pre-release of v2020.09.0rc1. It contains changes to garage since v2020.06.0.
This pre-release makes cutting-edge features available via PyPI, but comes with no promises of support or bug fixes. If you encounter problems with this release, you are encouraged to either install from master or revert to the v2020.06 release.
For information on what to expected in garage v2020.09, see the release notes for v2020.06.0
This is a maintenance release for 2019.10.
dm_control
from PyPI (#1406)advantages
shape in compute_advantage()
in torch tree (#1209)RaySampler
(#1583)