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 1211–1220 of 1262 papers

TitleStatusHype
Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits—0
Regret vs. Communication: Distributed Stochastic Multi-Armed Bandits and Beyond—0
Global Bandits—0
Networked Stochastic Multi-Armed Bandits with Combinatorial Strategies—0
Doubly Robust Policy Evaluation and Optimization—0
Learning to Search Better Than Your Teacher—0
Combinatorial Pure Exploration of Multi-Armed Bandits—0
Learning Multiple Tasks in Parallel with a Shared Annotator—0
Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback—0
On Minimax Optimal Offline Policy Evaluation—0
Show:102550
← PrevPage 122 of 127Next →

Benchmark Results

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