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 51–75 of 1262 papers

TitleStatusHype
Adaptive, Robust and Scalable Bayesian Filtering for Online Learning—0
Active Velocity Estimation using Light Curtains via Self-Supervised Multi-Armed Bandits—0
ADARES: Adaptive Resource Management for Virtual Machines—0
AdaLinUCB: Opportunistic Learning for Contextual Bandits—0
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health—0
Bandits with Knapsacks beyond the Worst-Case—0
Adversarial Attacks on Adversarial Bandits—0
Adapting Bandit Algorithms for Settings with Sequentially Available Arms—0
Adversarial Attacks on Cooperative Multi-agent Bandits—0
Adversarial Attacks on Linear Contextual Bandits—0
Adversarial Bandits with Knapsacks—0
Adversarial Contextual Bandits Go Kernelized—0
Active Search for High Recall: a Non-Stationary Extension of Thompson Sampling—0
Adaptively Learning to Select-Rank in Online Platforms—0
A Central Limit Theorem, Loss Aversion and Multi-Armed Bandits—0
Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits—0
A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits—0
Active Reinforcement Learning: Observing Rewards at a Cost—0
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds—0
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits—0
Active Inference for Autonomous Decision-Making with Contextual Multi-Armed Bandits—0
Adaptive Exploration in Linear Contextual Bandit—0
Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits—0
A Model Selection Approach for Corruption Robust Reinforcement Learning—0
A Bandit Approach to Sequential Experimental Design with False Discovery Control—0
Show:102550
← PrevPage 3 of 51Next →

Benchmark Results

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