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 151–160 of 1262 papers

TitleStatusHype
A Convex Framework for Confounding Robust InferenceCode0
Doubly Robust Policy Evaluation and LearningCode0
Causal Contextual Bandits with Adaptive ContextCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Adaptive Data Depth via Multi-Armed BanditsCode0
Online Learning for Function Placement in Serverless ComputingCode0
Best Arm Identification with Fixed Budget: A Large Deviation PerspectiveCode0
Equal Opportunity in Online Classification with Partial FeedbackCode0
Bayesian Optimisation over Multiple Continuous and Categorical InputsCode0
Batched Multi-armed Bandits ProblemCode0
Show:102550
← PrevPage 16 of 127Next →

Benchmark Results

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