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 1–25 of 1262 papers

TitleStatusHype
Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards—0
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic EnvironmentsCode0
Adaptive Data Augmentation for Thompson Sampling—0
A General Framework for Off-Policy Learning with Partially-Observed Reward—0
Stochastic Multi-Objective Multi-Armed Bandits: Regret Definition and Algorithm—0
Collaborative Min-Max Regret in Grouped Multi-Armed Bandits—0
Meet Me at the Arm: The Cooperative Multi-Armed Bandits Problem with Shareable Arms—0
Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards—0
From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance AdaptationCode0
VirnyFlow: A Design Space for Responsible Model DevelopmentCode0
Quick-Draw Bandits: Quickly Optimizing in Nonstationary Environments with Extremely Many Arms—0
COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents—0
A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing—0
Offline Clustering of Linear Bandits: Unlocking the Power of Clusters in Data-Limited Environments—0
Test-Time Scaling of Diffusion Models via Noise Trajectory SearchCode0
KL-regularization Itself is Differentially Private in Bandits and RLHF—0
Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype—0
In-Domain African Languages Translation Using LLMs and Multi-armed Bandits—0
Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima—0
Human in the Loop Adaptive Optimization for Improved Time Series ForecastingCode0
High-dimensional Nonparametric Contextual Bandit Problem—0
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis—0
Multi-Armed Bandits Meet Large Language Models—0
Batched Nonparametric Bandits via k-Nearest Neighbor UCB—0
Near Optimal Best Arm Identification for Clustered Bandits—0
Show:102550
← PrevPage 1 of 51Next →

Benchmark Results

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