CS Colloquium: Yuanzhi Li (CMU) - Multi-player Multi-armed Bandit: Can We Collaborate Without "Zoom"?
Tue, Nov 03, 2020 @ 03:30 PM - 04:30 PM
Conferences, Lectures, & Seminars
Speaker: Yuanzhi Li, Carnegie Mellon University
Talk Title: Multi-player Multi-armed Bandit: Can We Collaborate Without "Zoom"?
Series: Computer Science Colloquium
Abstract: Multi-armed bandit is a well-established area in online decision making, where one player makes sequential decisions in a non-stationary environment to maximize his/her accumulative rewards. The traditional multi-armed bandit problem becomes significantly more challenging when there are multiple players in the same environment, while only one piece of reward is presented at a time for each arm. In this setting, if two players pick the same arm at the same round, they are only able to get one piece of reward instead of two. When the rewards are non-negative, to maximize the total accumulative rewards by all players, they need to collaborate to avoid "collision" -- i.e. the players need to make sure that they do not all rush to the same arm (even if it has the highest reward) at the same round. We focus on the setting where communications between players are completely disabled: e.g. they are separated in different places of the world without any "Zoom". We show that low-regret can still be obtained in this setting: Players can actually collaborate to maximize total rewards by avoiding collision in a non-stationary environment, even when they do not communicate at all during the entire sequence of decisions.
Register in advance for this webinar at:
After registering, attendees will receive a confirmation email containing information about joining the webinar.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Yuanzhi Li is an assistant professor at CMU, Machine Learning Department. He did his Ph.D. at Princeton, under the advice of Sanjeev Arora (2014-2018) as well as a one-year postdoc at Stanford. His wife is Yandi Jin.
Host: Haipeng Luo
More Info: https://usc.zoom.us/webinar/register/WN_kVp5jz5qSIKAZIphNGWaWw
Location: Online Zoom Webinar
Audiences: Everyone Is Invited
Contact: Computer Science Department