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 751–775 of 1262 papers

TitleStatusHype
Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits—0
OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits—0
PAC-Bayesian Analysis of Contextual Bandits—0
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits—0
PAC-Bayesian Offline Contextual Bandits With Guarantees—0
PAC Identification of Many Good Arms in Stochastic Multi-Armed Bandits—0
PAC Reinforcement Learning with Rich Observations—0
Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy—0
Parallel Contextual Bandits in Wireless Handover Optimization—0
Parallelizing Contextual Bandits—0
Parameterized Exploration—0
Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback—0
Partially Observable Contextual Bandits with Linear Payoffs—0
Personalization Paradox in Behavior Change Apps: Lessons from a Social Comparison-Based Personalized App for Physical Activity—0
Personalized Course Sequence Recommendations—0
Perturbed-History Exploration in Stochastic Multi-Armed Bandits—0
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
Show:102550
← PrevPage 31 of 51Next →

Benchmark Results

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