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 126–150 of 1262 papers

TitleStatusHype
Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic maskingCode0
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingCode0
Doubly-Robust Lasso BanditCode0
Contextual Bandits with Stochastic ExpertsCode0
Contextual Bandits with Large Action Spaces: Made PracticalCode0
Contextual Linear Bandits under Noisy Features: Towards Bayesian OraclesCode0
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic EnvironmentsCode0
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex NetworksCode0
A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed BanditsCode0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Corralling a Band of Bandit AlgorithmsCode0
Conditionally Risk-Averse Contextual BanditsCode0
Constrained regret minimization for multi-criterion multi-armed banditsCode0
Contextual bandits with entropy-based human feedbackCode0
Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action SpacesCode0
Censored Semi-Bandits: A Framework for Resource Allocation with Censored FeedbackCode0
Causally Abstracted Multi-armed BanditsCode0
A New Bandit Setting Balancing Information from State Evolution and Corrupted ContextCode0
Combinatorial Bandits under Strategic ManipulationsCode0
Decentralized Cooperative Stochastic BanditsCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Causal Contextual Bandits with Adaptive ContextCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Best Arm Identification with Fixed Budget: A Large Deviation PerspectiveCode0
Show:102550
← PrevPage 6 of 51Next →

Benchmark Results

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