AI Paper Atlas

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

In-Context Learning for Pure Exploration

Alessio Russo, Ryan Welch, Aldo Pacchiano

ICLR 2026 · Bandits and online learning › Multi-armed bandits · approach: Pure exploration algorithms · 2 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
meta-train ICPE with learned inference network and RL query policy on binary searchICPE · Probabilistic binary search, K up to 256accuracy and max stopping time: min accuracy 1.00; max stop time equals log2 K (8 at K=256)Improved
learn the query policy with RL instead of acting greedily on the posterior (I-DPT) (ablation)ICPE · Stochastic bandits, fixed confidence delta=0.1stopping-time tail and correctnessImproved
use learned ICPE vs Track-and-Stop / Top-Two stopping rulesICPE · Stochastic bandits, fixed confidencesample complexity vs correctnessMixed
evaluate under shifted bandit distributionsICPE · Stochastic bandits, distribution shiftcorrectness and stopping timeNo clear effect
use ICPE instead of I-IDS on magic-action banditsICPE · Bandits with hidden information, delta=0.1sample complexityImproved
use ICPE vs uniform and Deep CMAB on MNIST pixel samplingICPE · MNIST pixel sampling, N=12accuracyImproved

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