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 71–80 of 1262 papers

TitleStatusHype
Active Feature Selection for the Mutual Information CriterionCode0
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex NetworksCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous AgentsCode0
Conditionally Risk-Averse Contextual BanditsCode0
Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action SpacesCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Adaptive Data Depth via Multi-Armed BanditsCode0
Causal Contextual Bandits with Adaptive ContextCode0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
Show:102550
← PrevPage 8 of 127Next →

Benchmark Results

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