OMX Helsinki — S&P 500 — DAX — NASDAQ 100 — STOXX 600 — EUR/USD — EUR/SEK — BTC/USD — ETH/USD — Euribor 3M — Euribor 12M —
Microsoft Research

Microsoft Research

Technology and AI 359,000 subscribers

Recharging Bandits

10.04.2018 1,580 views
Published: 10.04.2018 Category: Technology and AI Views: 1,580

Episode details

Episode description

We introduce a general model of bandit problems in which the expected payout of an arm is an increasing concave function of the time since it was last played. We first develop approximation algorithms for the underlying optimization problem of determining a reward-maximizing sequence of arm pulls. We then show how to use these algorithms in a learning setting to obtain sublinear regret. See more at https://www.microsoft.com/en-us/research/video/recharging-bandits/

Open the AI assistant chat. The chat loads only when you open it.