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 826–850 of 1262 papers

TitleStatusHype
Multi-Armed Bandits and Quantum Channel Oracles—0
Multi-armed Bandits: Competing with Optimal Sequences—0
Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback—0
Multi-Armed Bandits for Intelligent Tutoring Systems—0
Multi-armed Bandits for Link Configuration in Millimeter-wave Networks—0
Multi-Armed Bandits for Minesweeper: Profiting from Exploration-Exploitation Synergy—0
Multi-Armed Bandits in Metric Spaces—0
Multi-Armed Bandits Meet Large Language Models—0
Multi-armed bandits on implicit metric spaces—0
Multi-Armed Bandits on Partially Revealed Unit Interval Graphs—0
Multi-Armed Bandits with Abstention—0
Multi-armed Bandits with Application to 5G Small Cells—0
Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization—0
Multi-Armed Bandits with Censored Consumption of Resources—0
Multi-armed Bandits with Compensation—0
Multi-armed Bandits with Cost Subsidy—0
Multi-Armed Bandits with Dependent Arms—0
Multi-Armed Bandits with Generalized Temporally-Partitioned Rewards—0
Multi-Armed Bandits with Interference—0
Multi-Armed Bandits with Local Differential Privacy—0
Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards—0
Multi-Armed Bandits with Metric Movement Costs—0
Multi-Armed Bandits with Self-Information Rewards—0
Multi-Fidelity Multi-Armed Bandits Revisited—0
Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness—0
Show:102550
← PrevPage 34 of 51Next →

Benchmark Results

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