AI Paper Atlas

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

From Finite to Countable-Armed Bandits

Anand Kalvit, Assaf J. Zeevi

NeurIPS 2020 · Bandits and online learning › Multi-armed bandits · approach: Non-stationary and structured-reward bandits

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
increase gap Delta from small to largeALG(UCB1,Theta,2) bound · Monte-Carlo, Bernoulli rewardsbeta_DeltaImproved
small gap Delta toward 0ALG(UCB1,Theta,2) bound · Monte-Carlo, Bernoulli rewardsbeta_DeltaHurt
use UCB1 instead of Thompson Sampling in zero-gap two-armed bandittwo-armed bandit with Bernoulli(0.5) arms · fraction of plays of arm 1 at n=10,000concentration around 1/2Improved
use Thompson Sampling with Gaussian priors instead of Beta priorsThompson Sampling · zero-gap two-armed banditdistribution of play fractionMixed
increase UCB exploration parameter rhoUCB(rho) · zero-gap vs well-separated instancestail of play fraction vs regretMixed

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