Chao Tao

It’s a great question. From the design perspective, I think we should not let the learner communicate with the bandit directly since we can not prevent the learner from hacking...

I have re-checked your `decentralizedbaiprotocol` and made some modifications. Not sure I have did it right. Anyway, we should be careful about the decentralized best arm identification protocol.

Can you help move these algorithms under the current branch?

Thanks for being interested in the implementation. I am currently in the process of graduation. I will add them in the near future.

Good idea. BTW, I have invited you as one of the collaborators. Now you can push prs directly to the master branch. You can add me to the reviewer if...

I also added a rule to the master branch such that every pr needs at least one of our approvals.