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 541–550 of 1262 papers

TitleStatusHype
Bandits with Temporal Stochastic Constraints—0
Almost Boltzmann Exploration—0
CorrAttack: Black-box Adversarial Attack with Structured Search—0
Bandits with Partially Observable Confounded Data—0
Coordination without communication: optimal regret in two players multi-armed bandits—0
Coordinated Multi-Armed Bandits for Improved Spatial Reuse in Wi-Fi—0
Bandits with Knapsacks beyond the Worst Case—0
Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits—0
Adaptive Discretization against an Adversary: Lipschitz bandits, Dynamic Pricing, and Auction Tuning—0
A Correction of Pseudo Log-Likelihood Method—0
Show:102550
← PrevPage 55 of 127Next →

Benchmark Results

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