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 81–90 of 1262 papers

TitleStatusHype
Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information—0
Solving Inverse Problem for Multi-armed Bandits via Convex OptimizationCode0
Multi-agent Multi-armed Bandit with Fully Heavy-tailed Dynamics—0
Offline Learning for Combinatorial Multi-armed Bandits—0
Contextual Online Decision Making with Infinite-Dimensional Functional Regression—0
Breaking the (1/Δ_2) Barrier: Better Batched Best Arm Identification with Adaptive Grids—0
Sequential Learning of the Pareto Front for Multi-objective BanditsCode0
HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits Problems—0
Restless Multi-armed Bandits under Frequency and Window Constraints for Public Service Inspections—0
Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy—0
Show:102550
← PrevPage 9 of 127Next →

Benchmark Results

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