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 1091–1100 of 1262 papers

TitleStatusHype
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms—0
Greybox fuzzing as a contextual bandits problem—0
Finding the bandit in a graph: Sequential search-and-stop—0
Mitigating Bias in Adaptive Data Gathering via Differential Privacy—0
A General Framework for Bandit Problems Beyond Cumulative Objectives—0
The Externalities of Exploration and How Data Diversity Helps Exploitation—0
Myopic Bayesian Design of Experiments via Posterior Sampling and Probabilistic ProgrammingCode0
Learning Contextual Bandits in a Non-stationary EnvironmentCode0
Multi-Statistic Approximate Bayesian Computation with Multi-Armed Bandits—0
Bandit-Based Monte Carlo Optimization for Nearest NeighborsCode0
Show:102550
← PrevPage 110 of 127Next →

Benchmark Results

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