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 721–730 of 1262 papers

TitleStatusHype
Invariant Policy Learning: A Causal PerspectiveCode0
Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits—0
Parallelizing Contextual Bandits—0
Diffusion Approximations for Thompson Sampling—0
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep NetworksCode1
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Stochastic Multi-Armed Bandits with Control Variates—0
Contextual Bandits with Sparse Data in Web setting—0
Policy Learning with Adaptively Collected DataCode0
Optimal Algorithms for Range Searching over Multi-Armed Bandits—0
Show:102550
← PrevPage 73 of 127Next →

Benchmark Results

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