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 531–540 of 1262 papers

TitleStatusHype
GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits—0
Global Bandits—0
Global Rewards in Restless Multi-Armed Bandits—0
Gradient-free Online Learning in Continuous Games with Delayed Rewards—0
Graph Clustering Bandits for Recommendation—0
Graph-Dependent Regret Bounds in Multi-Armed Bandits with Interference—0
Practical Contextual Bandits with Feedback Graphs—0
Graph Neural Bandits—0
Greedy Algorithm almost Dominates in Smoothed Contextual Bandits—0
From Bandits to Experts: On the Value of Side-Observations—0
Show:102550
← PrevPage 54 of 127Next →

Benchmark Results

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