Chao Tao

The algorithm proposed in this paper is for a variant of the ordinary contextual bandit. We probably do not have plan to include it in the library currently. But contextual...

Which algorithms are you referring to? Could you provide the link?

`EXP3` is currently implemented in the ordinary multi-armed bandit.

Hi Chester, Thanks. That's a great suggestion! Actually, I have been considering implementing the communication protocol in our recent paper "Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration...

That's interesting. I am curious why collision is needed in pure exploration setting?

I see. It sounds an interesting direction.

I made some minor change. Have you used `pylint`? It is a tool to make your code more stylized.

I tried `flake8` (a wrapper of `pep8`). And I gave up since there are too many comments. It was a pain to customize it. Not sure this plugin is easier...

Just refactored the structure.

Just finshed refactoring singleplayer policy. You can sync and take a look.