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
Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making—0
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems—0
Continuous K-Max Bandits—0
Continuous-Time Multi-Armed Bandits with Controlled Restarts—0
Convex Hull Monte-Carlo Tree Search—0
Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs—0
Cooperative Stochastic Multi-agent Multi-armed Bandits Robust to Adversarial Corruptions—0
Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms—0
Coordinated Multi-Armed Bandits for Improved Spatial Reuse in Wi-Fi—0
Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits—0
Show:102550
← PrevPage 32 of 127Next →

Benchmark Results

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