Search Mailing List Archives
[theory-seminar] [theory-lunch] Bobby Kleinberg on Recharging bandits
hongyang at cs.stanford.edu
Sun Dec 3 17:38:38 PST 2017
This coming Thursday we are very excited to have Bobby Kleinberg giving a
special theory lunch. The talk is titled *Recharging Bandits: Learning to
Schedule Recurring Interventions *(the abstract follows below).
The talk will be from *12:15pm to 1:15pm at Gates 463A*, with lunch served
at noon. Please be on time for the talk and the food, as we will start
earlier than usual.
TITLE: Recharging Bandits: Learning to Schedule Recurring Interventions
Traditional multi-armed bandit models posit that the payoff distribution of
each action (or "arm") is stationary over time, and hence that the goal of
learning is to identify the arm with the highest expected payoff and choose
that one forever after. However, in many applications the efficacy of an
action depends on the amount of time that has elapsed since it was last
performed. Examples arise in precision agriculture, online education, and
music recommendations. In this talk we introduce a generalization of the
multi-armed bandit problem that models such applications. In the course of
analyzing algorithms for this problem, we will encounter some interesting
combinatorial questions about coloring the integers subject to bounds on
the sizes of subintervals that exclude a given color.
This talk is based on joint work with Nicole Immorlica.
Hongyang Zhang （张泓洋）
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the theory-seminar