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 861–870 of 1262 papers

TitleStatusHype
Towards Tractable Optimism in Model-Based Reinforcement Learning—0
Open Problem: Model Selection for Contextual Bandits—0
Learning by Repetition: Stochastic Multi-armed Bandits under Priming Effect—0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Stochastic Bandits with Linear Constraints—0
Constrained regret minimization for multi-criterion multi-armed banditsCode0
Stochastic Network Utility Maximization with Unknown Utilities: Multi-Armed Bandits Approach—0
Finding All ε-Good Arms in Stochastic BanditsCode0
Non-Stationary Off-Policy Optimization—0
Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners—0
Show:102550
← PrevPage 87 of 127Next →

Benchmark Results

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