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 321–330 of 1262 papers

TitleStatusHype
Bandits with Partially Observable Confounded Data—0
CorrAttack: Black-box Adversarial Attack with Structured Search—0
Bandits with Temporal Stochastic Constraints—0
Almost Boltzmann Exploration—0
Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes—0
Corruption-robust exploration in episodic reinforcement learning—0
Cost-Aware Optimal Pairwise Pure Exploration—0
Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning—0
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models—0
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making—0
Show:102550
← PrevPage 33 of 127Next →

Benchmark Results

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