mirror of
https://github.com/saymrwulf/stable-baselines3.git
synced 2026-05-16 21:10:08 +00:00
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
1f0dd60b97
* removed policy from save, changed th.loads to map to device * found hack: catch pickle exception and trying th.load with mapping instead, otherwise raise exception with more information -> loading cuda on cpu raises exception -> leads to th.load with map being called * deleted todo * updated changelog * start of saving refactor * first working c * all tests pass, save refactored * - backwards compatibilty not always - make pytest all passing - make typing all passing * Fixes and simplify the save method * Remove unused param * Fix backward compat * Fix docstring |
||
|---|---|---|
| docs | ||
| scripts | ||
| tests | ||
| torchy_baselines | ||
| .coveragerc | ||
| .gitignore | ||
| LICENSE | ||
| Makefile | ||
| README.md | ||
| setup.cfg | ||
| setup.py | ||
Torchy Baselines
PyTorch version of Stable Baselines, a set of improved implementations of reinforcement learning algorithms.
NOTE: Python 3.6 is required!
Implemented Algorithms
-
A2C
-
CEM-RL (with TD3)
-
PPO
-
SAC
-
TD3
-
SDE support for A2C, PPO, SAC and TD3.
Roadmap
- cf github Roadmap
Run the Tests
pip install -e .[tests]
make pytest
Type check
pip install -e .[tests]
make type
Build the Documentation
pip install -e .[docs]
make docs
Spell check for the documentation:
make spelling
Citing the Project
To cite this repository in publications:
@misc{torchy-baselines,
author = {Raffin, Antonin and Dormann, Noah and Hill, Ashley and Ernestus, Maximilian and Gleave, Adam and Kanervisto, Anssi},
title = {Torchy Baselines},
year = {2019},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/araffin/torchy-baselines}},
}