About Congestion Control IV: Reinforcement Learning

[lc11007]

I've seen something about reinforcement learning on your blog, and I'm very interested in it. Do you have this code posted on githup?

[squidarth]

Hi there @lc11007! It is on github actually--I haven't formatted it nicely or made it super easy to parse, but if you're curious about the code, check out this notebook:

https://github.com/squidarth/network-performance-jupyter/blob/master/Network-Reinforcement-Learning.ipynb

and this code: https://github.com/squidarth/network-performance-jupyter/blob/master/src/ml_strategy.py

This doesn't include our latest results (those weren't run in a notebook), but should hopefully tell the story here. Let me know if you have other questions!

Thanks for the interest and for reading my post (I'm curious how you stumbled upon it too!)

[lc11007]

Thank you very much for your reply. I also do some work on network congestion control myself. Recently, I have been studying some congestion control related to machine learning. I happened to see your website on Google. I hope there are other questions to discuss with you.

[squidarth]

Yeah, let me know if you get a chance to look at my code and if you have any questions

[lc11007]

Thank you again for your reply.If there are other problems, I hope I can get your help again.

[squidarth]

sure, no problem