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 1011–1020 of 1262 papers

TitleStatusHype
Pessimism for Offline Linear Contextual Bandits using _p Confidence Sets—0
PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits—0
Phasic Diversity Optimization for Population-Based Reinforcement Learning—0
Non-Stationary Off-Policy Optimization—0
Player Modeling via Multi-Armed Bandits—0
Policy Gradients for Contextual Recommendations—0
Practical Algorithms for Best-K Identification in Multi-Armed Bandits—0
Practical Contextual Bandits with Regression Oracles—0
Preference-based Online Learning with Dueling Bandits: A Survey—0
Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms—0
Show:102550
← PrevPage 102 of 127Next →

Benchmark Results

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