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 831–840 of 1262 papers

TitleStatusHype
Remote Contextual Bandits—0
Replicability is Asymptotically Free in Multi-armed Bandits—0
Representation-Driven Reinforcement Learning—0
Representative Arm Identification: A fixed confidence approach to identify cluster representatives—0
Replicable Bandits—0
Residual Bootstrap Exploration for Bandit Algorithms—0
Resonance: Replacing Software Constants with Context-Aware Models in Real-time Communication—0
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism—0
Resource Allocation in NOMA-based Self-Organizing Networks using Stochastic Multi-Armed Bandits—0
Resourceful Contextual Bandits—0
Show:102550
← PrevPage 84 of 127Next →

Benchmark Results

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