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 226–250 of 1262 papers

TitleStatusHype
Sequential Decision Making with Expert Demonstrations under Unobserved HeterogeneityCode0
Generalized Linear Bandits with Limited AdaptivityCode0
Feel-Good Thompson Sampling for Contextual Dueling Bandits—0
Hypothesis Generation with Large Language ModelsCode2
On the Importance of Uncertainty in Decision-Making with Large Language Models—0
Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy—0
Nearly-tight Approximation Guarantees for the Improving Multi-Armed Bandits Problem—0
A Correction of Pseudo Log-Likelihood Method—0
Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making—0
Transfer in Sequential Multi-armed Bandits via Reward Samples—0
Phasic Diversity Optimization for Population-Based Reinforcement Learning—0
Cramming Contextual Bandits for On-policy Statistical Evaluation—0
ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment—0
Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning—0
A General Reduction for High-Probability Analysis with General Light-Tailed Distributions—0
LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits—0
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds—0
Federated Linear Contextual Bandits with Heterogeneous Clients—0
Investigating Gender Fairness in Machine Learning-driven Personalized Care for Chronic Pain—0
Batched Nonparametric Contextual Bandits—0
Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement—0
Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace RecoveryCode0
Multi-Armed Bandits with Abstention—0
Optimistic Information Directed Sampling—0
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health—0
Show:102550
← PrevPage 10 of 51Next →

Benchmark Results

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