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 1221–1230 of 1262 papers

TitleStatusHype
Bandits Warm-up Cold Recommender Systems—0
Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms—0
Lipschitz Bandits: Regret Lower Bounds and Optimal Algorithms—0
Reducing Dueling Bandits to Cardinal Bandits—0
Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems—0
Generalized Risk-Aversion in Stochastic Multi-Armed Bandits—0
Resourceful Contextual Bandits—0
Algorithms for multi-armed bandit problems—0
Taming the Monster: A Fast and Simple Algorithm for Contextual BanditsCode0
Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits—0
Show:102550
← PrevPage 123 of 127Next →

Benchmark Results

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