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 1231–1240 of 1262 papers

TitleStatusHype
Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems—0
Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget—0
Context-Aware Bandits—0
Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms—0
Contextual Bandit Applications in Customer Support Bot—0
Contextual Bandits and Imitation Learning via Preference-Based Active Queries—0
Contextual Bandits and Optimistically Universal Learning—0
Contextual Bandits Evolving Over Finite Time—0
Contextual Bandits for adapting to changing User preferences over time—0
Contextual Bandits for Advertising Budget Allocation—0
Show:102550
← PrevPage 124 of 127Next →

Benchmark Results

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