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 1201–1210 of 1262 papers

TitleStatusHype
A Survey on Contextual Multi-armed BanditsCode0
Episodic Multi-armed Bandits—0
Linear Contextual Bandits with Knapsacks—0
Selecting the best system and multi-armed bandits—0
Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits—0
Scalable Discrete Sampling as a Multi-Armed Bandit Problem—0
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives—0
Regulating Greed Over Time in Multi-Armed BanditsCode0
On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits—0
Thompson Sampling for Budgeted Multi-armed Bandits—0
Show:102550
← PrevPage 121 of 127Next →

Benchmark Results

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