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 481–490 of 1262 papers

TitleStatusHype
Vertical Federated Linear Contextual Bandits—0
Anytime-valid off-policy inference for contextual banditsCode1
Contextual bandits with concave rewards, and an application to fair ranking—0
Multi-agent Dynamic Algorithm ConfigurationCode1
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
ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits—0
Replicable Bandits—0
Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs—0
Show:102550
← PrevPage 49 of 127Next →

Benchmark Results

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