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 781–790 of 1262 papers

TitleStatusHype
Productization Challenges of Contextual Multi-Armed Bandits—0
Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization—0
Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems—0
Provable General Function Class Representation Learning in Multitask Bandits and MDPs—0
Provably and Practically Efficient Neural Contextual Bandits—0
Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks—0
Transfer Learning with Partially Observable Offline Data via Causal Bounds—0
Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback—0
Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits—0
Provably Optimal Algorithms for Generalized Linear Contextual Bandits—0
Show:102550
← PrevPage 79 of 127Next →

Benchmark Results

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