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 301–310 of 1262 papers

TitleStatusHype
Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study—0
When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric PerspectiveCode0
Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks—0
An Experimental Design for Anytime-Valid Causal Inference on Multi-Armed BanditsCode0
LLMs-augmented Contextual Bandit—0
Adversarial Attacks on Cooperative Multi-agent Bandits—0
Efficient Generalized Low-Rank Tensor Contextual Bandits—0
High-dimensional Linear Bandits with Knapsacks—0
Federated Linear Bandits with Finite Adversarial Actions—0
An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits—0
Show:102550
← PrevPage 31 of 127Next →

Benchmark Results

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