AI Paper Atlas

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

Boltzmann Exploration Done Right

Nicolò Cesa-Bianchi, Claudio Gentile, Gabor Lugosi, Gergely Neu

NeurIPS 2017 · Bandits and online learning › Multi-armed bandits · approach: Bandit formulations for ML problems · 25 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
Start with a constant learning rate, then use a gap- and horizon-dependent increasing scheduleBoltzmann exploration · Bounded-reward stochastic multi-armed banditsregret: R_T ≤ 16eK log T/Δ² + 9K/Δ²Improved
Replace empirical means with influence-function reward estimatesBGE · Heavy-tailed stochastic multi-armed bandits with bounded second momentsregret: The bound coincides with that of Theorem [ref], except that σ² is replaced by V.Improved
Use standard Boltzmann variants rather than uncertainty-scaled perturbationsBoltzmann exploration · Bernoulli bandit with malicious initializationidentification of the optimal armHurt
Use BGE instead of standard Boltzmann explorationBoltzmann exploration · Bernoulli bandit with malicious initializationempirical performanceImproved

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