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 961–970 of 1262 papers

TitleStatusHype
Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints—0
Thompson Sampling via Local UncertaintyCode0
Trend-responsive User Segmentation Enabling Traceable Publishing Insights. A Case Study of a Real-world Large-scale News Recommendation System—0
BanditRank: Learning to Rank Using Contextual Bandits—0
Smoothness-Adaptive Contextual BanditsCode0
Multi-User MABs with User Dependent Rewards for Uncoordinated Spectrum Access—0
Decentralized Heterogeneous Multi-Player Multi-Armed Bandits with Non-Zero Rewards on Collisions—0
Adaptive Exploration in Linear Contextual Bandit—0
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision ProcessesCode0
An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays—0
Show:102550
← PrevPage 97 of 127Next →

Benchmark Results

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