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 461–470 of 1262 papers

TitleStatusHype
Adversarial Attacks on Adversarial Bandits—0
A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback—0
Contextual Causal Bayesian Optimisation—0
Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits—0
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning—0
Quantum Heavy-tailed Bandits—0
Multi-Armed Bandits and Quantum Channel Oracles—0
Multi-armed Bandit Learning for TDMA Transmission Slot Scheduling and Defragmentation for Improved Bandwidth Usage—0
Best Arm Identification in Stochastic Bandits: Beyond β-optimality—0
Local Differential Privacy for Sequential Decision Making in a Changing Environment—0
Show:102550
← PrevPage 47 of 127Next →

Benchmark Results

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