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 1111–1120 of 1262 papers

TitleStatusHype
A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing—0
A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits—0
A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits—0
A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications—0
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity—0
A Survey of Risk-Aware Multi-Armed Bandits—0
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits—0
Asymptotically Optimal Regret for Black-Box Predict-then-Optimize—0
The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models—0
Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments—0
Show:102550
← PrevPage 112 of 127Next →

Benchmark Results

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