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 941–950 of 1262 papers

TitleStatusHype
Surrogate Objectives for Batch Policy Optimization in One-step Decision Making—0
Offline Contextual Bandits with High Probability Fairness GuaranteesCode0
Learning in Generalized Linear Contextual Bandits with Stochastic Delays—0
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric—0
Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits—0
Thompson Sampling for Multinomial Logit Contextual BanditsCode0
Contextual Combinatorial Conservative Bandits—0
Automatic Ensemble Learning for Online Influence Maximization—0
Corruption-robust exploration in episodic reinforcement learning—0
Contextual Bandits Evolving Over Finite Time—0
Show:102550
← PrevPage 95 of 127Next →

Benchmark Results

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