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

Showing 10911100 of 1262 papers

TitleStatusHype
Estimation of Warfarin Dosage with Reinforcement LearningCode0
Evaluating Deep Vs. Wide & Deep Learners As Contextual Bandits For Personalized Email Promo RecommendationsCode0
Model selection for contextual banditsCode0
Best Arm Identification with Fixed Budget: A Large Deviation PerspectiveCode0
Evolutionary Multi-Armed Bandits with Genetic Thompson SamplingCode0
Optimal Learning for Structured BanditsCode0
Conditionally Risk-Averse Contextual BanditsCode0
Tight Regret Bounds for Single-pass Streaming Multi-armed BanditsCode0
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Show:102550
← PrevPage 110 of 127Next →

Benchmark Results

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