Chester Holtz

Distributed Bandit setup

15

Hi, thanks for this - it's a really awesome work! I'm interested in the decentralized/distributed bandit setup. Do you have any pointers for extending your code - e.g. to support...

FYI [JMLR MOSS]

2

Could be a long-term prospect if you are interested: [http://www.jmlr.org/mloss/](http://www.jmlr.org/mloss/) Inspiration: [https://perso.crans.org/besson/articles/SMPyBandits.pdf](https://perso.crans.org/besson/articles/SMPyBandits.pdf)

Annealing schedule

1

Need a better way to specify annealing schedule. Right now it is hard coded.

Support free rotation of modules. Should not be difficult to implement on top of 90/45.

Code is mostly there - just need to verify correctness. Should also be room for optimization. See https://stackoverflow.com/a/33310617/11755721

Will keep track of roadmap here. - Single SA instance currently achieves ~3k moves/sec - Reintegration of RTree [Rtree stuff is already there, just need to verify] - Fix CPP-Taskflow...

RL-driven routing experiments

2

Hi, great work & thanks for releasing the code to your paper! Was wondering if there is any plan to open-source the rl-driven routing experiments discussed in section 4.4 of...

Hi - I saw your work at the workshop! Thanks for making your work available. I was wondering about your progress on real data. I have been having some difficulty...