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 861–870 of 1262 papers

TitleStatusHype
Restless and Uncertain: Robust Policies for Restless Bandits via Deep Multi-Agent Reinforcement Learning—0
Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks—0
Rotting Bandits—0
Rotting bandits are not harder than stochastic ones—0
Safe Linear Leveling Bandits—0
Safety-Aware Algorithms for Adversarial Contextual Bandit—0
The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity—0
Sample complexity of partition identification using multi-armed bandits—0
Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning—0
Satisficing Exploration for Deep Reinforcement Learning—0
Show:102550
← PrevPage 87 of 127Next →

Benchmark Results

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