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 421–430 of 1262 papers

TitleStatusHype
BanditQ: Fair Bandits with Guaranteed Rewards—0
Full Gradient Deep Reinforcement Learning for Average-Reward Criterion—0
Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms—0
Federated Learning for Heterogeneous Bandits with Unobserved Contexts—0
Adaptive Endpointing with Deep Contextual Multi-armed Bandits—0
An Empirical Evaluation of Federated Contextual Bandit Algorithms—0
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling—0
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits—0
Data Dependent Regret Guarantees Against General Comparators for Full or Bandit Feedback—0
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex NetworksCode0
Show:102550
← PrevPage 43 of 127Next →

Benchmark Results

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