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 1151–1175 of 1262 papers

TitleStatusHype
Combinatorial Multi-Armed Bandits with Filtered Feedback—0
Boundary Crossing Probabilities for General Exponential Families—0
Multi-Task Learning for Contextual Bandits—0
Combinatorial Semi-Bandits with Knapsacks—0
Practical Algorithms for Best-K Identification in Multi-Armed Bandits—0
Bandit Regret Scaling with the Effective Loss Range—0
Mostly Exploration-Free Algorithms for Contextual BanditsCode0
Value Directed Exploration in Multi-Armed Bandits with Structured Priors—0
On Kernelized Multi-armed Bandits—0
Efficient Benchmarking of NLP APIs using Multi-armed Bandits—0
Selective Harvesting over Networks—0
Horde of Bandits using Gaussian Markov Random Fields—0
Contextual Linear Bandits under Noisy Features: Towards Bayesian OraclesCode0
Provably Optimal Algorithms for Generalized Linear Contextual Bandits—0
QoS-Aware Multi-Armed Bandits—0
Rotting Bandits—0
Beyond the Hazard Rate: More Perturbation Algorithms for Adversarial Multi-armed Bandits—0
Learning to Use Learners' Advice—0
The Price of Differential Privacy For Online Learning—0
Corralling a Band of Bandit AlgorithmsCode0
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits—0
Active Search for Sparse Signals with Region Sensing—0
Multi-armed Bandits: Competing with Optimal Sequences—0
Bandit algorithms to emulate human decision making using probabilistic distortions—0
Fair Algorithms for Infinite and Contextual Bandits—0
Show:102550
← PrevPage 47 of 51Next →

Benchmark Results

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