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 501–510 of 1262 papers

TitleStatusHype
Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous ActionsCode0
PAC-Bayesian Offline Contextual Bandits With Guarantees—0
Conditionally Risk-Averse Contextual BanditsCode0
Fast Beam Alignment via Pure Exploration in Multi-armed BanditsCode0
Optimal Contextual Bandits with Knapsacks under Realizability via Regression OraclesCode0
Vertical Federated Linear Contextual Bandits—0
Contextual bandits with concave rewards, and an application to fair ranking—0
Simulated Contextual Bandits for Personalization Tasks from Recommendation DatasetsCode0
Maximum entropy exploration in contextual bandits with neural networks and energy based models—0
Constant regret for sequence prediction with limited advice—0
Show:102550
← PrevPage 51 of 127Next →

Benchmark Results

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