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 51–100 of 1262 papers

TitleStatusHype
Efficient Algorithms for Extreme BanditsCode0
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox OptimizationCode0
Estimation of Warfarin Dosage with Reinforcement LearningCode0
Addressing the Long-term Impact of ML Decisions via Policy RegretCode0
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewardsCode0
Fast Beam Alignment via Pure Exploration in Multi-armed BanditsCode0
Federated Multi-armed Bandits with PersonalizationCode0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Adapting multi-armed bandits policies to contextual bandits scenariosCode0
Finite-time Analysis of Globally Nonstationary Multi-Armed BanditsCode0
Empirical analysis of representation learning and exploration in neural kernel banditsCode0
Gaussian Gated Linear NetworksCode0
Empirical Likelihood for Contextual BanditsCode0
Fairness of Exposure in Online Restless Multi-armed BanditsCode0
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and GeneralizationCode0
Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual BanditsCode0
Doubly-Robust Lasso BanditCode0
Scalable Exploration via Ensemble++Code0
A New Bandit Setting Balancing Information from State Evolution and Corrupted ContextCode0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingCode0
Contextual Linear Bandits under Noisy Features: Towards Bayesian OraclesCode0
Active Feature Selection for the Mutual Information CriterionCode0
Corralling a Band of Bandit AlgorithmsCode0
Contextual Bandits with Large Action Spaces: Made PracticalCode0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
Constrained regret minimization for multi-criterion multi-armed banditsCode0
Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action SpacesCode0
Correlated Multi-armed Bandits with a Latent Random SourceCode0
(Almost) Free Incentivized Exploration from Decentralized Learning AgentsCode0
Contextual bandits with entropy-based human feedbackCode0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Doubly Robust Policy Evaluation and LearningCode0
Adaptive Experimentation with Delayed Binary FeedbackCode0
Contextual Bandits with Stochastic ExpertsCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit ApproachCode0
Adaptive Data Depth via Multi-Armed BanditsCode0
Decentralized Cooperative Stochastic BanditsCode0
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous AgentsCode0
Censored Semi-Bandits: A Framework for Resource Allocation with Censored FeedbackCode0
Adaptive Linear Estimating EquationsCode0
A Convex Framework for Confounding Robust InferenceCode0
Combinatorial Bandits under Strategic ManipulationsCode0
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex NetworksCode0
Bandit-Based Monte Carlo Optimization for Nearest NeighborsCode0
An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed BanditsCode0
Safe and Adaptive Decision-Making for Optimization of Safety-Critical Systems: The ARTEO AlgorithmCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Show:102550
← PrevPage 2 of 26Next →

Benchmark Results

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