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 161–170 of 1262 papers

TitleStatusHype
FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocation—0
Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints—0
Optimal Streaming Algorithms for Multi-Armed Bandits—0
Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits—0
Contextual Bandits with Arm Request Costs and Delays—0
Online Learning for Function Placement in Serverless ComputingCode0
Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?—0
How Does Variance Shape the Regret in Contextual Bandits?—0
Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensity—0
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing—0
Show:102550
← PrevPage 17 of 127Next →

Benchmark Results

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