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 671–680 of 1262 papers

TitleStatusHype
Deep Upper Confidence Bound Algorithm for Contextual Bandit Ranking of Information Selection—0
A Model Selection Approach for Corruption Robust Reinforcement Learning—0
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning—0
Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits—0
Batched Thompson Sampling—0
Adapting Bandit Algorithms for Settings with Sequentially Available Arms—0
Regularized-OFU: an efficient algorithm for general contextual bandit with optimization oracles—0
Causal Contextual Bandits with Targeted Interventions—0
Expected Improvement-based Contextual Bandits—0
Batched Bandits with Crowd Externalities—0
Show:102550
← PrevPage 68 of 127Next →

Benchmark Results

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