DLR-RM / stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
https://stable-baselines3.readthedocs.io
MIT License
8.68k stars 1.65k forks source link

[Feature Request] Implementation of QC_SANE #1258

Closed surbhigupta1908 closed 1 year ago

surbhigupta1908 commented 1 year ago

🚀 Feature

I have implemented QC_SANE DRL approach (pytorch framework) and want to add this as feature to this repo. Research Paper: https://ieeexplore.ieee.org/document/9640528

Motivation

To contribute to open source (stable baselines3) as this repo and its tensorflow implementations helped me a lot in understanding the implementation of DRL approaches.

Pitch

I want to provide the implementation of QC_SANE so that DRL community can leverage its implementation.

Alternatives

I have only pytorch implementation of QC_SANE. No other alternatives are available.

Additional context

No response

Checklist

araffin commented 1 year ago

Hello, this sounds more like something for SB3 contrib (see https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/issues/115 for instance) or for SB3 project list that we have in our doc.

surbhigupta1908 commented 1 year ago

Yes, it is for SB3 and my codes are prepared using (https://github.com/combra-lab/pop-spiking-deep-rl) as base repo. I have arranged the files according tot SB3 file structure for seamless integration.