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 131–140 of 1262 papers

TitleStatusHype
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
Diminishing Exploration: A Minimalist Approach to Piecewise Stationary Multi-Armed Bandits—0
EVOLvE: Evaluating and Optimizing LLMs For Exploration—0
Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks—0
Stochastic Bandits for Egalitarian Assignment—0
Show:102550
← PrevPage 14 of 127Next →

Benchmark Results

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