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 891–900 of 1262 papers

TitleStatusHype
NeuralUCB: Contextual Bandits with Neural Network-Based Exploration—0
No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guarantees—0
Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits—0
Nonparametric Contextual Bandits in an Unknown Metric Space—0
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric—0
Nonparametric Stochastic Contextual Bandits—0
Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling—0
Adversarial Rewards in Universal Learning for Contextual Bandits—0
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset—0
Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach—0
Show:102550
← PrevPage 90 of 127Next →

Benchmark Results

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