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 661–670 of 1262 papers

TitleStatusHype
FLASH: Federated Learning Across Simultaneous Heterogeneities—0
Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles—0
Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts—0
Foundations of Reinforcement Learning and Interactive Decision Making—0
From Bandits to Experts: A Tale of Domination and Independence—0
From Bandits to Experts: On the Value of Side-Observations—0
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses—0
Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information—0
Full Gradient Deep Reinforcement Learning for Average-Reward Criterion—0
Fully Gap-Dependent Bounds for Multinomial Logit Bandit—0
Show:102550
← PrevPage 67 of 127Next →

Benchmark Results

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