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 261–270 of 1262 papers

TitleStatusHype
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning—0
A Contextual Combinatorial Bandit Approach to Negotiation—0
A Blackbox Approach to Best of Both Worlds in Bandits and Beyond—0
Contextual Bandits for Evaluating and Improving Inventory Control Policies—0
Contextual Bandits and Optimistically Universal Learning—0
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis—0
Contextual Bandits and Imitation Learning via Preference-Based Active Queries—0
Contextual Bandit Applications in Customer Support Bot—0
Asymptotic Randomised Control with applications to bandits—0
A Federated Online Restless Bandit Framework for Cooperative Resource Allocation—0
Show:102550
← PrevPage 27 of 127Next →

Benchmark Results

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