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 551–575 of 1262 papers

TitleStatusHype
Communication Efficient Distributed Learning for Kernelized Contextual Bandits—0
Conformal Off-Policy Prediction in Contextual Bandits—0
Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits—0
Neural Bandit with Arm Group Graph—0
Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits—0
A Simple and Optimal Policy Design with Safety against Heavy-Tailed Risk for Stochastic Bandits—0
Group Meritocratic Fairness in Linear Contextual BanditsCode0
Robust Pareto Set Identification with Contaminated Bandit Feedback—0
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making—0
Contextual Bandits with Knapsacks for a Conversion Model—0
Provable General Function Class Representation Learning in Multitask Bandits and MDPs—0
Provably and Practically Efficient Neural Contextual Bandits—0
Online Meta-Learning in Adversarial Multi-Armed Bandits—0
Optimistic Whittle Index Policy: Online Learning for Restless BanditsCode0
Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets—0
Federated Neural BanditsCode0
Fairness and Welfare Quantification for Regret in Multi-Armed Bandits—0
Meta-Learning Adversarial Bandits—0
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits—0
Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment—0
Contextual Pandora's Box—0
Neural Contextual Bandits Based Dynamic Sensor Selection for Low-Power Body-Area Networks—0
Information-Directed Selection for Top-Two AlgorithmsCode0
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs—0
Falsification of Multiple Requirements for Cyber-Physical Systems Using Online Generative Adversarial Networks and Multi-Armed Bandits—0
Show:102550
← PrevPage 23 of 51Next →

Benchmark Results

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