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 1031–1040 of 1262 papers

TitleStatusHype
Better Algorithms for Stochastic Bandits with Adversarial Corruptions—0
AdaLinUCB: Opportunistic Learning for Contextual Bandits—0
Equal Opportunity in Online Classification with Partial FeedbackCode0
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting—0
A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free—0
Randomized Allocation with Nonparametric Estimation for Contextual Multi-Armed Bandits with Delayed Rewards—0
On the bias, risk and consistency of sample means in multi-armed bandits—0
Target Tracking for Contextual Bandits: Application to Demand Side Management—0
Almost Boltzmann Exploration—0
The Assistive Multi-Armed BanditCode0
Show:102550
← PrevPage 104 of 127Next →

Benchmark Results

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