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 801–825 of 1262 papers

TitleStatusHype
Finding All -Good Arms in Stochastic Bandits—0
A Tractable Online Learning Algorithm for the Multinomial Logit Contextual Bandit—0
Resonance: Replacing Software Constants with Context-Aware Models in Real-time Communication—0
Fully Gap-Dependent Bounds for Multinomial Logit Bandit—0
A New Bandit Setting Balancing Information from State Evolution and Corrupted ContextCode0
Reward Biased Maximum Likelihood Estimation for Reinforcement Learning—0
Metric-Free Individual Fairness with Cooperative Contextual Bandits—0
Improving Offline Contextual Bandits with Distributional Robustness—0
Active Reinforcement Learning: Observing Rewards at a Cost—0
Asymptotic Convergence of Thompson Sampling—0
Multi-armed Bandits with Cost Subsidy—0
Towards Fundamental Limits of Multi-armed Bandits with Random Walk Feedback—0
On No-Sensing Adversarial Multi-player Multi-armed Bandits with Collision Communications—0
Multi-Armed Bandits with Censored Consumption of Resources—0
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism—0
Learning to Actively Learn: A Robust Approach—0
Tractable contextual bandits beyond realizability—0
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards—0
Online Semi-Supervised Learning with Bandit Feedback—0
Online Algorithm for Unsupervised Sequential Selection with Contextual Information—0
Quantile Bandits for Best Arms IdentificationCode0
Achieving User-Side Fairness in Contextual Bandits—0
DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees—0
Stochastic Bandits with Vector Losses: Minimizing ^-Norm of Relative Losses—0
Asymptotic Randomised Control with applications to bandits—0
Show:102550
← PrevPage 33 of 51Next →

Benchmark Results

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