Private and Provably Efficient Federated Decision-Making
In this thesis, we study sequential multi-armed bandit and reinforcement learning in the federated setting, where a group of agents collaborates to improve their collective reward by communicating over a network. We first study the multi-armed bandit problem in a decentralized environment. We stu...
| Κύριος συγγραφέας: | |
|---|---|
| Άλλοι συγγραφείς: | |
| Μορφή: | Thesis |
| Έκδοση: |
Massachusetts Institute of Technology
2022
|
| Διαθέσιμο Online: | https://hdl.handle.net/1721.1/143222 |