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 1251–1262 of 1262 papers

TitleStatusHype
Approximating a Target Distribution using Weight QueriesCode0
Relational Boosted BanditsCode0
Efficient Algorithms for Extreme BanditsCode0
Multi-agent Multi-armed Bandits with Minimum Reward Guarantee FairnessCode0
VirnyFlow: A Design Space for Responsible Model DevelopmentCode0
Offline Contextual Bandits with High Probability Fairness GuaranteesCode0
The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many ArmsCode0
Optimal Baseline Corrections for Off-Policy Contextual BanditsCode0
Adaptive Data Depth via Multi-Armed BanditsCode0
Optimal Batched Linear BanditsCode0
Antithetic Sampling for Top-k Shapley IdentificationCode0
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox OptimizationCode0
Show:102550
← PrevPage 26 of 26Next →

Benchmark Results

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