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 1001–1010 of 1262 papers

TitleStatusHype
Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits—0
Value Directed Exploration in Multi-Armed Bandits with Structured Priors—0
Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency—0
Variance-Dependent Regret Lower Bounds for Contextual Bandits—0
Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits—0
Variational Inference for Model-Free and Model-Based Reinforcement Learning—0
Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences—0
Vertical Federated Linear Contextual Bandits—0
Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits—0
Bandit algorithms to emulate human decision making using probabilistic distortions—0
Show:102550
← PrevPage 101 of 127Next →

Benchmark Results

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