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 811–820 of 1262 papers

TitleStatusHype
Modeling Human Decision-making in Generalized Gaussian Multi-armed Bandits—0
Modelling Cournot Games as Multi-agent Multi-armed Bandits—0
Model selection for behavioral learning data and applications to contextual bandits—0
Model Selection for Generic Contextual Bandits—0
Model Selection in Contextual Stochastic Bandit Problems—0
Model Selection in Reinforcement Learning with General Function Approximations—0
Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysis—0
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning—0
More Robust Doubly Robust Off-policy Evaluation—0
Mortal Multi-Armed Bandits—0
Show:102550
← PrevPage 82 of 127Next →

Benchmark Results

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