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 311–320 of 1262 papers

TitleStatusHype
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling BanditsCode0
A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits—0
Contextual Bandits for Evaluating and Improving Inventory Control Policies—0
Off-Policy Evaluation for Large Action Spaces via Policy Convolution—0
Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization—0
α-Fair Contextual Bandits—0
Pure Exploration in Asynchronous Federated Bandits—0
Leveraging heterogeneous spillover in maximizing contextual bandit rewards—0
Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs—0
Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling—0
Show:102550
← PrevPage 32 of 127Next →

Benchmark Results

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