SOTAVerified

Multi-Armed Bandits

Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.

( Image credit: Microsoft Research )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 471–480 of 1262 papers

TitleStatusHype
Adaptive Data Depth via Multi-Armed BanditsCode0
Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless BanditsCode1
Revisiting Simple Regret: Fast Rates for Returning a Good Arm—0
Robust Contextual Linear Bandits—0
Conditionally Risk-Averse Contextual BanditsCode0
Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees—0
PAC-Bayesian Offline Contextual Bandits With Guarantees—0
Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous ActionsCode0
Fast Beam Alignment via Pure Exploration in Multi-armed BanditsCode0
Optimal Contextual Bandits with Knapsacks under Realizability via Regression OraclesCode0
Show:102550
← PrevPage 48 of 127Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NeuralLinear FullPosterior-MRCumulative regret1.92—Unverified
2Linear FullPosterior-MRCumulative regret1.82—Unverified