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 721–730 of 1262 papers

TitleStatusHype
On the Identification and Mitigation of Weaknesses in the Knowledge Gradient Policy for Multi-Armed Bandits—0
On the Importance of Uncertainty in Decision-Making with Large Language Models—0
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits—0
Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits—0
On the Problem of Best Arm Retention—0
Contextual Decision-Making with Knapsacks Beyond the Worst Case—0
On The Statistical Complexity of Offline Decision-Making—0
On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs—0
On Universally Optimal Algorithms for A/B Testing—0
Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture—0
Show:102550
← PrevPage 73 of 127Next →

Benchmark Results

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