AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Refining the Confidence Level for Optimistic Bandit Strategies

Tor Lattimore

JMLR 2018 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms · 62 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ADA-UCB's refined confidence level instead of UCB's log(t) levelstochastic Gaussian bandit · Worst-case regime, equal gaps (many arms)regret: UCB suffers about three times the regret of ADA-UCBImproved
use well-tuned confidence levels as the number of arms growsindex bandit policies · Worst-case regime, equal gapsregretImproved
replace MOSS, UCB, Thompson sampling and others with ADA-UCB20-armed Gaussian bandit · Regret versus horizon, k = 20regretImproved
use the log-term variant of MOSS from this paper instead of the Menard-Garivier log term (ablation)MOSS · Gaussian bandit experimentsregretImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy