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 1051–1060 of 1262 papers

TitleStatusHype
Towards Fundamental Limits of Multi-armed Bandits with Random Walk Feedback—0
Rarely-switching linear bandits: optimization of causal effects for the real world—0
Rate-Constrained Remote Contextual Bandits—0
Reciprocal Learning—0
Recommenadation aided Caching using Combinatorial Multi-armed Bandits—0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Incorporating Multi-armed Bandit with Local Search for MaxSATCode0
VITS : Variational Inference Thompson Sampling for contextual banditsCode0
Causal Contextual Bandits with Adaptive ContextCode0
Show:102550
← PrevPage 106 of 127Next →

Benchmark Results

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