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 191–200 of 1262 papers

TitleStatusHype
Best-of-Both-Worlds Linear Contextual Bandits—0
Better Algorithms for Stochastic Bandits with Adversarial Corruptions—0
Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multi-armed Bandits—0
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles—0
Bi-Criteria Optimization for Combinatorial Bandits: Sublinear Regret and Constraint Violation under Bandit Feedback—0
BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits—0
BOF-UCB: A Bayesian-Optimistic Frequentist Algorithm for Non-Stationary Contextual Bandits—0
Boltzmann Exploration Done Right—0
Balanced off-policy evaluation in general action spaces—0
Balanced Linear Contextual Bandits—0
Show:102550
← PrevPage 20 of 127Next →

Benchmark Results

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