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 801–810 of 1262 papers

TitleStatusHype
Queue Scheduling with Adversarial Bandit Learning—0
Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms—0
Raising Student Completion Rates with Adaptive Curriculum and Contextual Bandits—0
Random Effect Bandits—0
Randomized Allocation with Nonparametric Estimation for Contextual Multi-Armed Bandits with Delayed Rewards—0
Randomized Greedy Learning for Non-monotone Stochastic Submodular Maximization Under Full-bandit Feedback—0
Towards Fundamental Limits of Multi-armed Bandits with Random Walk Feedback—0
Rarely-switching linear bandits: optimization of causal effects for the real world—0
Rate-Constrained Remote Contextual Bandits—0
Reciprocal Learning—0
Show:102550
← PrevPage 81 of 127Next →

Benchmark Results

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