mlsanityData to 7 Oct 2026

Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting

arXiv 1902.01520 ↗First posted 5 Feb 2019stat.ML cs.LGcited by 42

Not on the map. Why?

Abstract (arXiv)

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-dependent "zooming" behavior and, with no tuning, yield improved guarantees for benign problems. We also study adapting to unknown smoothness parameters, establishing a price-of-adaptivity and deriving optimal adaptive algorithms that require no additional information.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 4; 2023: 11; 2024: 12; 2025: 5; 2026: 4.

42 papers.

Sort:

By area:

  1. 2022Jump-Start Reinforcement Learningcited by 102
  2. 2022Off-Policy Evaluation for Large Action Spaces via Embeddingscited by 53
  3. 2024Feedback Efficient Online Fine-Tuning of Diffusion Modelscited by 52
  4. 2022Contextual Bandits with Large Action Spaces: Made Practicalcited by 32
  5. 2021Lipschitz Bandits with Batched Feedbackcited by 21
  6. 2022Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spacescited by 17
  7. 2024Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learningcited by 16
  8. 2023Reliable Off-Policy Learning for Dosage Combinationscited by 15
  9. 2023Importance-Weighted Offline Learning Done Rightcited by 15
  10. 2023Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Banditscited by 14
  11. 2023Tracking Most Significant Shifts in Nonparametric Contextual Banditscited by 10
  12. 2021A Map of Bandits for E-commercecited by 9
30 more
  1. 2023A Lipschitz Bandits Approach for Continuous Hyperparameter Optimizationcited by 9
  2. 2023Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricingcited by 8
  3. 2024Probabilities of Causation for Continuous and Vector Variablescited by 8
  4. 2024Contextual Bandits for Unbounded Context Distributionscited by 8
  5. 2021Universal and data-adaptive algorithms for model selection in linear contextual banditscited by 5
  6. 2024Information Capacity Regret Bounds for Bandits with Mediator Feedbackcited by 4
  7. 2024A Parametric Contextual Online Learning Theory of Brokeragecited by 4
  8. 2024Adaptive Smooth Non-Stationary Banditscited by 4
  9. 2021Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimizationcited by 3
  10. 2023Optimal Exploration is no harder than Thompson Samplingcited by 3
  11. 2024Batched Nonparametric Contextual Banditscited by 3
  12. 2024DISCO: An End-to-End Bandit Framework for Personalised Discount Allocationcited by 3
  13. 2025Multiplayer Information Asymmetric Bandits in Metric Spacescited by 3
  14. 2021Coarse-Grained Smoothness for RL in Metric Spacescited by 2
  15. 2023Infinite Action Contextual Bandits with Reusable Data Exhaustcited by 2
  16. 2024Batched Stochastic Bandit for Nondegenerate Functionscited by 2
  17. 2024A Complete Characterization of Learnability for Stochastic Noisy Banditscited by 2
  18. 2025Learning to Decide with Just Enough: Information-Theoretic Context Summarization for CMDPscited by 2
  19. 2026Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Banditscited by 2
  20. 2024GuideLight: "Industrial Solution" Guidance for More Practical Traffic Signal Control Agentscited by 1
  21. 2025Lipschitz Bandits with Stochastic Delayed Feedbackcited by 1
  22. 2021An Analysis of Reinforcement Learning for Malaria Controlcited by 0
  23. 2023Efficient Learning for Selecting Top-m Context-Dependent Designscited by 0
  24. 2023From Random Search to Bandit Learning in Metric Measure Spacescited by 0
  25. 2023Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instancescited by 0
  26. 2025Batched Bandits with Heavy-Tailed Rewardscited by 0
  27. 2025Contextual Dynamic Pricing with Heterogeneous Buyerscited by 0
  28. 2026RIE-Greedy: Regularization-Induced Exploration for Contextual Banditscited by 0
  29. 2026Instance-Adaptive Online Multicalibrationcited by 0
  30. 2026Nonparametric Contextual Pricing and Inventory Learning under Censored Demandcited by 0