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 31–40 of 1262 papers

TitleStatusHype
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed BanditsCode1
Efficient Contextual Bandits with Continuous ActionsCode1
Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RLCode1
Hierarchical Adaptive Contextual Bandits for Resource Constraint based RecommendationCode1
A Modern Introduction to Online LearningCode1
Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous NetworksCode1
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions ModelingCode1
Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards—0
A General Framework for Off-Policy Learning with Partially-Observed Reward—0
Adaptive Data Augmentation for Thompson Sampling—0
Show:102550
← PrevPage 4 of 127Next →

Benchmark Results

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