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 1181–1190 of 1262 papers

TitleStatusHype
BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits—0
Boltzmann Exploration Done Right—0
Bootstrapping Upper Confidence Bound—0
Boundary Crossing Probabilities for General Exponential Families—0
Bounded Regret for Finitely Parameterized Multi-Armed Bandits—0
Breaking the (1/Δ_2) Barrier: Better Batched Best Arm Identification with Adaptive Grids—0
Breaking the T Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits—0
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism—0
Budget-Constrained Multi-Armed Bandits with Multiple Plays—0
Budgeted Combinatorial Multi-Armed Bandits—0
Show:102550
← PrevPage 119 of 127Next →

Benchmark Results

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