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 51–75 of 1262 papers

TitleStatusHype
Contextual Bandits with Large Action Spaces: Made PracticalCode0
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox OptimizationCode0
Contextual Bandits with Stochastic ExpertsCode0
Addressing the Long-term Impact of ML Decisions via Policy RegretCode0
A New Bandit Setting Balancing Information from State Evolution and Corrupted ContextCode0
Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit ApproachCode0
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewardsCode0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
Contextual bandits with entropy-based human feedbackCode0
Correlated Multi-armed Bandits with a Latent Random SourceCode0
Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual BanditsCode0
Doubly Robust Policy Evaluation and OptimizationCode0
Adaptive Linear Estimating EquationsCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous AgentsCode0
Scalable Exploration via Ensemble++Code0
Censored Semi-Bandits: A Framework for Resource Allocation with Censored FeedbackCode0
Combinatorial Bandits under Strategic ManipulationsCode0
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex NetworksCode0
Adaptive Experimentation with Delayed Binary FeedbackCode0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Active Feature Selection for the Mutual Information CriterionCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Causal Contextual Bandits with Adaptive ContextCode0
Show:102550
← PrevPage 3 of 51Next →

Benchmark Results

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