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 441–450 of 1262 papers

TitleStatusHype
Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits—0
Causal Feature Selection Method for Contextual Multi-Armed Bandits in Recommender System—0
Equipping Experts/Bandits with Long-term Memory—0
Adapting to Misspecification in Contextual Bandits—0
Estimating Optimal Policy Value in General Linear Contextual Bandits—0
Estimation Considerations in Contextual Bandits—0
Expanding on Repeated Consumer Search Using Multi-Armed Bandits and Secretaries—0
Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems—0
From Predictions to Decisions: The Importance of Joint Predictive Distributions—0
Constant regret for sequence prediction with limited advice—0
Show:102550
← PrevPage 45 of 127Next →

Benchmark Results

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