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 101–125 of 1262 papers

TitleStatusHype
Estimation of Warfarin Dosage with Reinforcement LearningCode0
Evaluating Deep Vs. Wide & Deep Learners As Contextual Bandits For Personalized Email Promo RecommendationsCode0
Fast Beam Alignment via Pure Exploration in Multi-armed BanditsCode0
Combinatorial Bandits under Strategic ManipulationsCode0
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox OptimizationCode0
Federated Neural BanditsCode0
From Restless to Contextual: A Thresholding Bandit Approach to Improve Finite-horizon PerformanceCode0
From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance AdaptationCode0
Censored Semi-Bandits: A Framework for Resource Allocation with Censored FeedbackCode0
Antithetic Sampling for Top-k Shapley IdentificationCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Causal Contextual Bandits with Adaptive ContextCode0
AC-Band: A Combinatorial Bandit-Based Approach to Algorithm ConfigurationCode0
Human in the Loop Adaptive Optimization for Improved Time Series ForecastingCode0
Causally Abstracted Multi-armed BanditsCode0
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous AgentsCode0
Constrained regret minimization for multi-criterion multi-armed banditsCode0
Incorporating Multi-armed Bandit with Local Search for MaxSATCode0
Adapting multi-armed bandits policies to contextual bandits scenariosCode0
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement LearningCode0
Invariant Policy Learning: A Causal PerspectiveCode0
Inverse Contextual Bandits: Learning How Behavior Evolves over TimeCode0
Best Arm Identification with Fixed Budget: A Large Deviation PerspectiveCode0
Kernel Conditional Moment Constraints for Confounding Robust InferenceCode0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
Show:102550
← PrevPage 5 of 51Next →

Benchmark Results

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