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 1101–1125 of 1262 papers

TitleStatusHype
PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits—0
Delegating via Quitting Games—0
Combining Difficulty Ranking with Multi-Armed Bandits to Sequence Educational Content—0
Best arm identification in multi-armed bandits with delayed feedback—0
What Doubling Tricks Can and Can't Do for Multi-Armed Bandits—0
Semiparametric Contextual BanditsCode0
Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback—0
Online learning over a finite action set with limited switching—0
Practical Contextual Bandits with Regression Oracles—0
The K-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates—0
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingCode0
Contextual Bandits with Stochastic ExpertsCode0
Regional Multi-Armed Bandits—0
Online Learning with an Unknown Fairness Metric—0
Multi-Armed Bandits on Partially Revealed Unit Interval Graphs—0
Policy Gradients for Contextual Recommendations—0
More Robust Doubly Robust Off-policy Evaluation—0
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits—0
Nonparametric Stochastic Contextual Bandits—0
Contextual memory bandit for pro-active dialog engagement—0
Residual Loss Prediction: Reinforcement Learning With No Incremental FeedbackCode0
Learning Structural Weight Uncertainty for Sequential Decision-MakingCode0
Active Search for High Recall: a Non-Stationary Extension of Thompson Sampling—0
Stochastic Multi-armed Bandits in Constant Space—0
Gaussian Process bandits with adaptive discretization—0
Show:102550
← PrevPage 45 of 51Next →

Benchmark Results

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