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 371–380 of 1262 papers

TitleStatusHype
Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity ConstraintsCode0
On Universally Optimal Algorithms for A/B Testing—0
Clustered Linear Contextual Bandits with Knapsacks—0
Graph Neural Bandits—0
Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit ApproachCode0
AdaptEx: A Self-Service Contextual Bandit Platform—0
Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs—0
Transfer Learning with Partially Observable Offline Data via Causal Bounds—0
Online Matching: A Real-time Bandit System for Large-scale RecommendationsCode0
Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems—0
Show:102550
← PrevPage 38 of 127Next →

Benchmark Results

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