2019-09-26 09:46:40 +00:00
|
|
|
.. _changelog:
|
|
|
|
|
|
|
|
|
|
Changelog
|
|
|
|
|
==========
|
|
|
|
|
|
2020-02-14 13:39:24 +00:00
|
|
|
|
|
|
|
|
Pre-Release 0.3.0a0 (WIP)
|
2020-01-20 15:19:35 +00:00
|
|
|
------------------------------
|
2019-09-26 09:46:40 +00:00
|
|
|
|
2020-02-14 13:39:24 +00:00
|
|
|
Breaking Changes:
|
|
|
|
|
^^^^^^^^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
New Features:
|
|
|
|
|
^^^^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
Bug Fixes:
|
|
|
|
|
^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
Deprecations:
|
|
|
|
|
^^^^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
Others:
|
|
|
|
|
^^^^^^^
|
2020-02-21 13:50:28 +00:00
|
|
|
- SAC with SDE now sample only one matrix
|
2020-02-14 13:39:24 +00:00
|
|
|
|
|
|
|
|
Documentation:
|
|
|
|
|
^^^^^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Pre-Release 0.2.0 (2020-02-14)
|
|
|
|
|
------------------------------
|
|
|
|
|
|
|
|
|
|
**Python 3.6+ required, type checking, callbacks, doc build**
|
|
|
|
|
|
2019-09-26 09:46:40 +00:00
|
|
|
Breaking Changes:
|
|
|
|
|
^^^^^^^^^^^^^^^^^
|
2020-01-22 16:23:42 +00:00
|
|
|
- Python 2 support was dropped, Torchy Baselines now requires Python 3.6 or above
|
2020-01-27 14:57:34 +00:00
|
|
|
- Return type of `evaluation.evaluate_policy()` has been changed
|
2020-02-03 14:50:40 +00:00
|
|
|
- Refactored the replay buffer to avoid transformation between PyTorch and NumPy
|
2020-02-05 12:10:02 +00:00
|
|
|
- Created `OffPolicyRLModel` base class
|
2020-02-14 12:42:16 +00:00
|
|
|
- Remove deprecated JSON format for `Monitor`
|
2019-09-26 09:46:40 +00:00
|
|
|
|
|
|
|
|
New Features:
|
|
|
|
|
^^^^^^^^^^^^^
|
2020-01-22 16:25:08 +00:00
|
|
|
- Add `seed()` method to `VecEnv` class
|
2020-01-27 13:32:31 +00:00
|
|
|
- Add support for Callback (cf https://github.com/hill-a/stable-baselines/pull/644)
|
2020-02-05 12:10:02 +00:00
|
|
|
- Add methods for saving and loading replay buffer
|
2020-02-11 15:40:44 +00:00
|
|
|
- Add `extend()` method to the buffers
|
2020-02-12 10:34:29 +00:00
|
|
|
- Add `get_vec_normalize_env()` to `BaseRLModel` to retrieve `VecNormalize` wrapper when it exists
|
2020-02-12 14:25:05 +00:00
|
|
|
- Add `results_plotter` from Stable Baselines
|
|
|
|
|
- Improve `predict()` method to handle different type of observations (single, vectorized, ...)
|
2019-09-26 09:46:40 +00:00
|
|
|
|
|
|
|
|
Bug Fixes:
|
|
|
|
|
^^^^^^^^^^
|
2020-01-31 12:06:55 +00:00
|
|
|
- Fix loading model on CPU that were trained on GPU
|
2020-01-31 12:16:28 +00:00
|
|
|
- Fix `reset_num_timesteps` that was not used
|
2020-02-11 16:22:03 +00:00
|
|
|
- Fix entropy computation for squashed Gaussian (approximate it now)
|
|
|
|
|
- Fix seeding when using multiple environments (different seed per env)
|
2019-09-26 09:46:40 +00:00
|
|
|
|
|
|
|
|
Deprecations:
|
|
|
|
|
^^^^^^^^^^^^^
|
|
|
|
|
|
2020-01-20 15:19:35 +00:00
|
|
|
Others:
|
|
|
|
|
^^^^^^^
|
2020-01-22 16:23:42 +00:00
|
|
|
- Add type check
|
|
|
|
|
- Converted all format string to f-strings
|
2020-01-27 13:32:31 +00:00
|
|
|
- Add test for `OrnsteinUhlenbeckActionNoise`
|
2020-01-27 14:57:34 +00:00
|
|
|
- Add type aliases in `common.type_aliases`
|
2020-01-20 15:19:35 +00:00
|
|
|
|
|
|
|
|
Documentation:
|
|
|
|
|
^^^^^^^^^^^^^^
|
|
|
|
|
- fix documentation build
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Pre-Release 0.1.0 (2020-01-20)
|
|
|
|
|
------------------------------
|
|
|
|
|
**First Release: base algorithms and state-dependent exploration**
|
|
|
|
|
|
|
|
|
|
Breaking Changes:
|
|
|
|
|
^^^^^^^^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
New Features:
|
|
|
|
|
^^^^^^^^^^^^^
|
|
|
|
|
- Initial release of A2C, CEM-RL, PPO, SAC and TD3, working only with `Box` input space
|
|
|
|
|
- State-Dependent Exploration (SDE) for A2C, PPO, SAC and TD3
|
|
|
|
|
|
|
|
|
|
Bug Fixes:
|
|
|
|
|
^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
Deprecations:
|
|
|
|
|
^^^^^^^^^^^^^
|
|
|
|
|
|
2019-09-26 09:46:40 +00:00
|
|
|
Others:
|
|
|
|
|
^^^^^^^
|
|
|
|
|
|
|
|
|
|
Documentation:
|
|
|
|
|
^^^^^^^^^^^^^^
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Maintainers
|
|
|
|
|
-----------
|
|
|
|
|
|
|
|
|
|
Torchy-Baselines is currently maintained by `Antonin Raffin`_ (aka `@araffin`_).
|
|
|
|
|
|
|
|
|
|
.. _Antonin Raffin: https://araffin.github.io/
|
|
|
|
|
.. _@araffin: https://github.com/araffin
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Contributors:
|
|
|
|
|
-------------
|
|
|
|
|
In random order...
|
|
|
|
|
|
|
|
|
|
Thanks to @hill-a @enerijunior @AdamGleave @Miffyli
|
