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 541–550 of 1262 papers

TitleStatusHype
Greedy Bandits with Sampled Context—0
Greybox fuzzing as a contextual bandits problem—0
Contextual Bandits for adapting to changing User preferences over time—0
Guaranteed Fixed-Confidence Best Arm Identification in Multi-Armed Bandits: Simple Sequential Elimination Algorithms—0
GuideBoot: Guided Bootstrap for Deep Contextual Bandits—0
Contextual Bandits for Advertising Budget Allocation—0
Hawkes Process Multi-armed Bandits for Disaster Search and Rescue—0
HD-CB: The First Exploration of Hyperdimensional Computing for Contextual Bandits Problems—0
Heterogeneous Multi-Agent Bandits with Parsimonious Hints—0
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses—0
Show:102550
← PrevPage 55 of 127Next →

Benchmark Results

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