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
Federated Combinatorial Multi-Agent Multi-Armed Bandits—0
Federated Linear Bandits with Finite Adversarial Actions—0
Federated Linear Contextual Bandits—0
Federated Linear Contextual Bandits with Heterogeneous Clients—0
Federated Linear Contextual Bandits with User-level Differential Privacy—0
Conservative Contextual Bandits: Beyond Linear Representations—0
Federated Multi-Armed Bandits Under Byzantine Attacks—0
Combinatorial Semi-Bandits with Knapsacks—0
Combining Difficulty Ranking with Multi-Armed Bandits to Sequence Educational Content—0
Conformal Off-Policy Prediction in Contextual Bandits—0
Show:102550
← PrevPage 49 of 127Next →

Benchmark Results

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