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 1241–1250 of 1262 papers

TitleStatusHype
Addressing the Long-term Impact of ML Decisions via Policy RegretCode0
Test-Time Scaling of Diffusion Models via Noise Trajectory SearchCode0
Regulating Greed Over Time in Multi-Armed BanditsCode0
Safe Exploration for Optimizing Contextual BanditsCode0
Simulated Contextual Bandits for Personalization Tasks from Recommendation DatasetsCode0
Reinforcement Learning for Physical Layer CommunicationsCode0
Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic BanditsCode0
Mostly Exploration-Free Algorithms for Contextual BanditsCode0
Scalable Exploration via Ensemble++Code0
The Assistive Multi-Armed BanditCode0
Show:102550
← PrevPage 125 of 127Next →

Benchmark Results

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