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 181–190 of 1262 papers

TitleStatusHype
Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards—0
On Speeding Up Language Model Evaluation—0
Honor Among Bandits: No-Regret Learning for Online Fair Division—0
A Contextual Combinatorial Bandit Approach to Negotiation—0
Classical Bandit Algorithms for Entanglement Detection in Parameterized Qubit States—0
Jump Starting Bandits with LLM-Generated Prior KnowledgeCode0
EduQate: Generating Adaptive Curricula through RMABs in Education Settings—0
BEACON: Balancing Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes—0
Discovering Minimal Reinforcement Learning EnvironmentsCode1
Towards Bayesian Data Selection—0
Show:102550
← PrevPage 19 of 127Next →

Benchmark Results

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