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 21–30 of 1262 papers

TitleStatusHype
High-dimensional Nonparametric Contextual Bandit Problem—0
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis—0
Multi-Armed Bandits Meet Large Language Models—0
Near Optimal Best Arm Identification for Clustered Bandits—0
Batched Nonparametric Bandits via k-Nearest Neighbor UCB—0
Adaptive, Robust and Scalable Bayesian Filtering for Online Learning—0
Navigating the Rashomon Effect: How Personalization Can Help Adjust Interpretable Machine Learning Models to Individual Users—0
Adaptive Budgeted Multi-Armed Bandits for IoT with Dynamic Resource Constraints—0
Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms—0
Access Probability Optimization in RACH: A Multi-Armed Bandits Approach—0
Show:102550
← PrevPage 3 of 127Next →

Benchmark Results

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