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 726–750 of 1262 papers

TitleStatusHype
On Learning to Rank Long Sequences with Contextual Bandits—0
Multi-facet Contextual Bandits: A Neural Network PerspectiveCode0
Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks—0
Differentially Private Multi-Armed Bandits in the Shuffle Model—0
Fair Exploration via Axiomatic Bargaining—0
Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits—0
Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions—0
Addressing the Long-term Impact of ML Decisions via Policy RegretCode0
Invariant Policy Learning: A Causal PerspectiveCode0
Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits—0
Parallelizing Contextual Bandits—0
Diffusion Approximations for Thompson Sampling—0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Stochastic Multi-Armed Bandits with Control Variates—0
Contextual Bandits with Sparse Data in Web setting—0
Policy Learning with Adaptively Collected DataCode0
Optimal Algorithms for Range Searching over Multi-Armed Bandits—0
Statistical Inference with M-Estimators on Adaptively Collected Data—0
Online certification of preference-based fairness for personalized recommender systems—0
Off-Policy Risk Assessment in Contextual Bandits—0
Censored Semi-Bandits for Resource Allocation—0
An Efficient Algorithm for Deep Stochastic Contextual Bandits—0
Leveraging Good Representations in Linear Contextual Bandits—0
Multinomial Logit Contextual Bandits: Provable Optimality and Practicality—0
Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information—0
Show:102550
← PrevPage 30 of 51Next →

Benchmark Results

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