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 631–640 of 1262 papers

TitleStatusHype
Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization—0
Online Fair Revenue Maximizing Cake Division with Non-Contiguous Pieces in Adversarial Bandits—0
Offline Neural Contextual Bandits: Pessimism, Optimization and GeneralizationCode1
Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Bandits—0
Offline Contextual Bandits for Wireless Network Optimization—0
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit—0
Universal and data-adaptive algorithms for model selection in linear contextual bandits—0
Empirical analysis of representation learning and exploration in neural kernel banditsCode0
Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits—0
Bandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits—0
Show:102550
← PrevPage 64 of 127Next →

Benchmark Results

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