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 1141–1150 of 1262 papers

TitleStatusHype
Variational inference for the multi-armed contextual banditCode0
Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads—0
Efficient Contextual Bandits in Non-stationary Worlds—0
Reinforcement learning techniques for Outer Loop Link Adaptation in 4G/5G systems—0
Safety-Aware Algorithms for Adversarial Contextual Bandit—0
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity—0
Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits—0
Efficient Reinforcement Learning via Initial Pure Exploration—0
Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration—0
Boltzmann Exploration Done Right—0
Show:102550
← PrevPage 115 of 127Next →

Benchmark Results

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