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 421–430 of 1262 papers

TitleStatusHype
Efficient Contextual Bandits with Uninformed Feedback Graphs—0
Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits—0
Delegating via Quitting Games—0
Delay-Adaptive Learning in Generalized Linear Contextual Bandits—0
An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Bandits—0
Efficient Generalized Low-Rank Tensor Contextual Bandits—0
Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems—0
Deep Upper Confidence Bound Algorithm for Contextual Bandit Ranking of Information Selection—0
Deep Contextual Bandits for Fast Initial Access in mmWave Based User-Centric Ultra-Dense Networks—0
Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching—0
Show:102550
← PrevPage 43 of 127Next →

Benchmark Results

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