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 791–800 of 1262 papers

TitleStatusHype
A One-Size-Fits-All Solution to Conservative Bandit Problems—0
Active Feature Selection for the Mutual Information CriterionCode0
Adversarial Linear Contextual Bandits with Graph-Structured Side Observations—0
Streaming Algorithms for Stochastic Multi-armed Bandits—0
Efficient Automatic CASH via Rising Bandits—0
Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits—0
Neural Contextual Bandits with Deep Representation and Shallow Exploration—0
Distributed Thompson Sampling—0
Batched Coarse Ranking in Multi-Armed Bandits—0
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many ArmsCode0
Show:102550
← PrevPage 80 of 127Next →

Benchmark Results

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