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 161–170 of 1262 papers

TitleStatusHype
Faster Q-Learning Algorithms for Restless Bandits—0
Performance-Aware Self-Configurable Multi-Agent Networks: A Distributed Submodular Approach for Simultaneous Coordination and Network DesignCode0
Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits—0
Contextual Bandit with Herding Effects: Algorithms and Recommendation Applications—0
Representative Arm Identification: A fixed confidence approach to identify cluster representatives—0
Online Fair Division with Contextual Bandits—0
Dynamic Product Image Generation and Recommendation at Scale for Personalized E-commerce—0
Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards—0
Multi-agent Multi-armed Bandits with Stochastic Sharable Arm Capacities—0
Contextual Bandits for Unbounded Context Distributions—0
Show:102550
← PrevPage 17 of 127Next →

Benchmark Results

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