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 926–950 of 1262 papers

TitleStatusHype
A General Theory of the Stochastic Linear Bandit and Its Applications—0
Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles—0
Adversarial Attacks on Linear Contextual Bandits—0
Inference for Batched Bandits—0
Selfish Robustness and Equilibria in Multi-Player Bandits—0
The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity—0
A Closer Look at Small-loss Bounds for Bandits with Graph Feedback—0
Safe Exploration for Optimizing Contextual BanditsCode0
Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits—0
Bandits with Knapsacks beyond the Worst-Case—0
Ballooning Multi-Armed Bandits—0
Incentivising Exploration and Recommendations for Contextual Bandits with Payments—0
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits—0
Gradient-free Online Learning in Continuous Games with Delayed Rewards—0
Exploration Through Bias: Revisiting Biased Maximum Likelihood Estimation in Stochastic Multi-Armed Bandits—0
Fair Contextual Multi-Armed Bandits: Theory and Experiments—0
Sublinear Optimal Policy Value Estimation in Contextual Bandits—0
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric—0
Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits—0
Thompson Sampling for Multinomial Logit Contextual BanditsCode0
Offline Contextual Bandits with High Probability Fairness GuaranteesCode0
Learning in Generalized Linear Contextual Bandits with Stochastic Delays—0
Surrogate Objectives for Batch Policy Optimization in One-step Decision Making—0
Contextual Combinatorial Conservative Bandits—0
Automatic Ensemble Learning for Online Influence Maximization—0
Show:102550
← PrevPage 38 of 51Next →

Benchmark Results

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