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 201–250 of 1262 papers

TitleStatusHype
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
On-line Adaptative Curriculum Learning for GANsCode0
Online Matching: A Real-time Bandit System for Large-scale RecommendationsCode0
Online Semi-Supervised Learning in Contextual Bandits with Episodic RewardCode0
The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many ArmsCode0
Optimal Baseline Corrections for Off-Policy Contextual BanditsCode0
Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound FrameworkCode0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
Optimistic Whittle Index Policy: Online Learning for Restless BanditsCode0
Output-Weighted Sampling for Multi-Armed Bandits with Extreme PayoffsCode0
Constrained regret minimization for multi-criterion multi-armed banditsCode0
Performance-Aware Self-Configurable Multi-Agent Networks: A Distributed Submodular Approach for Simultaneous Coordination and Network DesignCode0
Model selection for contextual banditsCode0
Conditionally Risk-Averse Contextual BanditsCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Power Constrained BanditsCode0
Practical Calculation of Gittins Indices for Multi-armed BanditsCode0
Causal Contextual Bandits with Adaptive ContextCode0
Addressing the Long-term Impact of ML Decisions via Policy RegretCode0
Quantile Bandits for Best Arms IdentificationCode0
Causally Abstracted Multi-armed BanditsCode0
Censored Semi-Bandits: A Framework for Resource Allocation with Censored FeedbackCode0
Contextual bandits with entropy-based human feedbackCode0
Regulating Greed Over Time in Multi-Armed BanditsCode0
Relational Boosted BanditsCode0
Residual Loss Prediction: Reinforcement Learning With No Incremental FeedbackCode0
Semiparametric Contextual BanditsCode0
Sequential Decision Making with Expert Demonstrations under Unobserved HeterogeneityCode0
SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed BanditsCode0
Simulated Contextual Bandits for Personalization Tasks from Recommendation DatasetsCode0
Approximating a Target Distribution using Weight QueriesCode0
Combinatorial Bandits under Strategic ManipulationsCode0
Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit ApproachCode0
Stochastic Rising BanditsCode0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
The Assistive Multi-Armed BanditCode0
Thompson Sampling for Bandit Learning in Matching MarketsCode0
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With RenegingCode0
Thompson Sampling via Local UncertaintyCode0
Top-k eXtreme Contextual Bandits with Arm HierarchyCode0
Towards the D-Optimal Online Experiment Design for Recommender SelectionCode0
Networked Restless Bandits with Positive ExternalitiesCode0
Two-Stage Neural Contextual Bandits for Personalised News RecommendationCode0
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits—0
Adversarial Contextual Bandits Go Kernelized—0
Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensity—0
A Survey of Risk-Aware Multi-Armed Bandits—0
Communication Efficient Distributed Learning for Kernelized Contextual Bandits—0
Adversarial Bandits with Knapsacks—0
Show:102550
← PrevPage 5 of 26Next →

Benchmark Results

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