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 111–120 of 1262 papers

TitleStatusHype
Selective Reviews of Bandit Problems in AI via a Statistical View—0
Contextual Bandits in Payment Processing: Non-uniform Exploration and Supervised Learning at Adyen—0
Achieving PAC Guarantees in Mechanism Design through Multi-Armed Bandits—0
Off-policy estimation with adaptively collected data: the power of online learning—0
A unifying framework for generalised Bayesian online learning in non-stationary environmentsCode1
Multi-Agent Stochastic Bandits Robust to Adversarial Corruptions—0
Individual Regret in Cooperative Stochastic Multi-Armed Bandits—0
Variance-Aware Linear UCB with Deep Representation for Neural Contextual BanditsCode0
Multi-armed Bandits with Missing OutcomeCode0
Structure Matters: Dynamic Policy Gradient—0
Show:102550
← PrevPage 12 of 127Next →

Benchmark Results

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