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 151–160 of 1262 papers

TitleStatusHype
Individual Regret in Cooperative Stochastic Multi-Armed Bandits—0
Multi-armed Bandits with Missing OutcomeCode0
Variance-Aware Linear UCB with Deep Representation for Neural Contextual BanditsCode0
Structure Matters: Dynamic Policy Gradient—0
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF—0
Rising Rested Bandits: Lower Bounds and Efficient Algorithms—0
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset—0
PageRank Bandits for Link PredictionCode0
MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings—0
Minimum Empirical Divergence for Sub-Gaussian Linear BanditsCode0
Show:102550
← PrevPage 16 of 127Next →

Benchmark Results

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