mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-11-18 09:54:10 +00:00
Doc fix and add Stable-Baselines3 Jax (SBX) page (#1566)
* Fix custom policy example * Add RL Zoo doc link * Add changelog to pypi * Add SBX doc page * Fix small mistake in docstring --------- Co-authored-by: Peter Elmers <peter.elmers@yahoo.com>
This commit is contained in:
parent
f667f086ea
commit
4fdb65ecf3
8 changed files with 77 additions and 5 deletions
|
|
@ -73,7 +73,7 @@ Goals of this repository:
|
||||||
|
|
||||||
Github repo: https://github.com/DLR-RM/rl-baselines3-zoo
|
Github repo: https://github.com/DLR-RM/rl-baselines3-zoo
|
||||||
|
|
||||||
Documentation: https://stable-baselines3.readthedocs.io/en/master/guide/rl_zoo.html
|
Documentation: https://rl-baselines3-zoo.readthedocs.io/en/master/
|
||||||
|
|
||||||
## SB3-Contrib: Experimental RL Features
|
## SB3-Contrib: Experimental RL Features
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -371,7 +371,8 @@ If your task requires even more granular control over the policy/value architect
|
||||||
*args,
|
*args,
|
||||||
**kwargs,
|
**kwargs,
|
||||||
):
|
):
|
||||||
|
# Disable orthogonal initialization
|
||||||
|
kwargs["ortho_init"] = False
|
||||||
super().__init__(
|
super().__init__(
|
||||||
observation_space,
|
observation_space,
|
||||||
action_space,
|
action_space,
|
||||||
|
|
@ -380,8 +381,7 @@ If your task requires even more granular control over the policy/value architect
|
||||||
*args,
|
*args,
|
||||||
**kwargs,
|
**kwargs,
|
||||||
)
|
)
|
||||||
# Disable orthogonal initialization
|
|
||||||
self.ortho_init = False
|
|
||||||
|
|
||||||
def _build_mlp_extractor(self) -> None:
|
def _build_mlp_extractor(self) -> None:
|
||||||
self.mlp_extractor = CustomNetwork(self.features_dim)
|
self.mlp_extractor = CustomNetwork(self.features_dim)
|
||||||
|
|
|
||||||
|
|
@ -17,6 +17,8 @@ Goals of this repository:
|
||||||
3. Provide tuned hyperparameters for each environment and RL algorithm
|
3. Provide tuned hyperparameters for each environment and RL algorithm
|
||||||
4. Have fun with the trained agents!
|
4. Have fun with the trained agents!
|
||||||
|
|
||||||
|
Documentation is available online: https://rl-baselines3-zoo.readthedocs.io/
|
||||||
|
|
||||||
Installation
|
Installation
|
||||||
------------
|
------------
|
||||||
|
|
||||||
|
|
|
||||||
66
docs/guide/sbx.rst
Normal file
66
docs/guide/sbx.rst
Normal file
|
|
@ -0,0 +1,66 @@
|
||||||
|
.. _sbx:
|
||||||
|
|
||||||
|
==========================
|
||||||
|
Stable Baselines Jax (SBX)
|
||||||
|
==========================
|
||||||
|
|
||||||
|
`Stable Baselines Jax (SBX) <https://github.com/araffin/sbx>`_ is a proof of concept version of Stable-Baselines3 in Jax.
|
||||||
|
|
||||||
|
It provides a minimal number of features compared to SB3 but can be much faster (up to 20x times!): https://twitter.com/araffin2/status/1590714558628253698
|
||||||
|
|
||||||
|
Implemented algorithms:
|
||||||
|
|
||||||
|
- Soft Actor-Critic (SAC) and SAC-N
|
||||||
|
- Truncated Quantile Critics (TQC)
|
||||||
|
- Dropout Q-Functions for Doubly Efficient Reinforcement Learning (DroQ)
|
||||||
|
- Proximal Policy Optimization (PPO)
|
||||||
|
- Deep Q Network (DQN)
|
||||||
|
|
||||||
|
|
||||||
|
As SBX follows SB3 API, it is also compatible with the `RL Zoo <https://github.com/DLR-RM/rl-baselines3-zoo>`_.
|
||||||
|
For that you will need to create two files:
|
||||||
|
|
||||||
|
``train_sbx.py``:
|
||||||
|
|
||||||
|
.. code-block:: python
|
||||||
|
|
||||||
|
import rl_zoo3
|
||||||
|
import rl_zoo3.train
|
||||||
|
from rl_zoo3.train import train
|
||||||
|
from sbx import DQN, PPO, SAC, TQC, DroQ
|
||||||
|
|
||||||
|
|
||||||
|
rl_zoo3.ALGOS["tqc"] = TQC
|
||||||
|
rl_zoo3.ALGOS["droq"] = DroQ
|
||||||
|
rl_zoo3.ALGOS["sac"] = SAC
|
||||||
|
rl_zoo3.ALGOS["ppo"] = PPO
|
||||||
|
rl_zoo3.ALGOS["dqn"] = DQN
|
||||||
|
rl_zoo3.train.ALGOS = rl_zoo3.ALGOS
|
||||||
|
rl_zoo3.exp_manager.ALGOS = rl_zoo3.ALGOS
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
train()
|
||||||
|
|
||||||
|
Then you can call ``python train_sbx.py --algo sac --env Pendulum-v1`` and use the RL Zoo CLI.
|
||||||
|
|
||||||
|
|
||||||
|
``enjoy_sbx.py``:
|
||||||
|
|
||||||
|
.. code-block:: python
|
||||||
|
|
||||||
|
import rl_zoo3
|
||||||
|
import rl_zoo3.enjoy
|
||||||
|
from rl_zoo3.enjoy import enjoy
|
||||||
|
from sbx import DQN, PPO, SAC, TQC, DroQ
|
||||||
|
|
||||||
|
|
||||||
|
rl_zoo3.ALGOS["tqc"] = TQC
|
||||||
|
rl_zoo3.ALGOS["droq"] = DroQ
|
||||||
|
rl_zoo3.ALGOS["sac"] = SAC
|
||||||
|
rl_zoo3.ALGOS["ppo"] = PPO
|
||||||
|
rl_zoo3.ALGOS["dqn"] = DQN
|
||||||
|
rl_zoo3.enjoy.ALGOS = rl_zoo3.ALGOS
|
||||||
|
rl_zoo3.exp_manager.ALGOS = rl_zoo3.ALGOS
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
enjoy()
|
||||||
|
|
@ -51,6 +51,7 @@ Main Features
|
||||||
guide/integrations
|
guide/integrations
|
||||||
guide/rl_zoo
|
guide/rl_zoo
|
||||||
guide/sb3_contrib
|
guide/sb3_contrib
|
||||||
|
guide/sbx
|
||||||
guide/imitation
|
guide/imitation
|
||||||
guide/migration
|
guide/migration
|
||||||
guide/checking_nan
|
guide/checking_nan
|
||||||
|
|
|
||||||
|
|
@ -80,6 +80,8 @@ Documentation:
|
||||||
- Added ``EvalCallback`` example (@sidney-tio)
|
- Added ``EvalCallback`` example (@sidney-tio)
|
||||||
- Update custom env documentation
|
- Update custom env documentation
|
||||||
- Added `pink-noise-rl` to projects page
|
- Added `pink-noise-rl` to projects page
|
||||||
|
- Fix custom policy example, ``ortho_init`` was ignored
|
||||||
|
- Added SBX page
|
||||||
|
|
||||||
|
|
||||||
Release 1.8.0 (2023-04-07)
|
Release 1.8.0 (2023-04-07)
|
||||||
|
|
|
||||||
1
setup.py
1
setup.py
|
|
@ -159,6 +159,7 @@ setup(
|
||||||
project_urls={
|
project_urls={
|
||||||
"Code": "https://github.com/DLR-RM/stable-baselines3",
|
"Code": "https://github.com/DLR-RM/stable-baselines3",
|
||||||
"Documentation": "https://stable-baselines3.readthedocs.io/",
|
"Documentation": "https://stable-baselines3.readthedocs.io/",
|
||||||
|
"Changelog": "https://stable-baselines3.readthedocs.io/en/master/misc/changelog.html",
|
||||||
"SB3-Contrib": "https://github.com/Stable-Baselines-Team/stable-baselines3-contrib",
|
"SB3-Contrib": "https://github.com/Stable-Baselines-Team/stable-baselines3-contrib",
|
||||||
"RL-Zoo": "https://github.com/DLR-RM/rl-baselines3-zoo",
|
"RL-Zoo": "https://github.com/DLR-RM/rl-baselines3-zoo",
|
||||||
},
|
},
|
||||||
|
|
|
||||||
|
|
@ -202,7 +202,7 @@ class ResultsWriter:
|
||||||
|
|
||||||
def write_row(self, epinfo: Dict[str, float]) -> None:
|
def write_row(self, epinfo: Dict[str, float]) -> None:
|
||||||
"""
|
"""
|
||||||
Close the file handler
|
Write row of monitor data to csv log file.
|
||||||
|
|
||||||
:param epinfo: the information on episodic return, length, and time
|
:param epinfo: the information on episodic return, length, and time
|
||||||
"""
|
"""
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue