dodox/fancy_rl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

TODO and WIP warning for README

Browse Source
This commit is contained in:
Dominik Moritz Roth 2024-06-02 16:18:11 +02:00
parent 7861821d0d
commit 6cb320f432
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -8,6 +8,9 @@
Fancy RL provides a minimalistic and efficient implementation of Proximal Policy Optimization (PPO) and Trust Region Policy Layers (TRPL) using primitives from [torchrl](https://pypi.org/project/torchrl/). This library focuses on providing clean, understandable code and reusable modules while leveraging the powerful functionalities of torchrl.
| :exclamation: This project is still WIP and not ready to be used. |
| ------------------------------------------------------------ |
## Installation
Fancy RL requires Python 3.7-3.11. (TorchRL currently does not support Python 3.12)
@ -49,6 +52,17 @@ To run the test suite:
pytest test/test_ppo.py
```
## TODO
- [ ] Test / Benchmark PPO
- [ ] Refactor Modules for TRPL
- [ ] Get TRPL working
- [ ] Test / Benchmark TRPL
- [ ] Make contextual covariance optional
- [ ] Allow full-cov via chol
- [ ] Write docs / extend README
- [ ] (Implement SAC?)
## Contributing
Contributions are welcome! Feel free to open issues or submit pull requests to enhance the library.