mlsanityData to 7 Oct 2026

Bandits with Partially Observable Confounded Data

arXiv 2006.06731 ↗First posted 11 Jun 2020cs.LG cs.AI stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

We study linear contextual bandits with access to a large, confounded, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We construct a linear bandit algorithm that takes advantage of the projected information, and prove regret bounds. Our results demonstrate the ability to take advantage of confounded offline data. Particularly, we prove regret bounds that improve current bounds by a factor related to the visible dimensionality of the contexts in the data. Our results indicate that confounded offline data can significantly improve online learning algorithms. Finally, we demonstrate various characteristics of our approach through synthetic simulations.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 8; 2024: 3; 2025: 2; 2026: 2.

22 papers.

Sort:

By area:

  1. 2023A Survey on Causal Reinforcement Learningcited by 43
  2. 2022Leveraging Offline Data in Online Reinforcement Learningcited by 42
  3. 2023Causal Deep Learningcited by 20
  4. 2021Invariant Policy Learning: A Causal Perspectivecited by 17
  5. 2021On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learningcited by 14
  6. 2023Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounderscited by 12
  7. 2021Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Banditscited by 10
  8. 2023Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confoundingcited by 7
  9. 2023Online Decision Mediationcited by 4
  10. 2022Efficient Algorithms for Learning to Control Bandits with Unobserved Contextscited by 3
  11. 2025Linear Bandits with Partially Observable Featurescited by 3
  12. 2022Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observationscited by 2
10 more
  1. 2023A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observationscited by 2
  2. 2024Predictive Performance Comparison of Decision Policies Under Confoundingcited by 2
  3. 2023Robustly Improving Bandit Algorithms with Confounded and Selection Biased Offline Data: A Causal Approachcited by 1
  4. 2024Contextual Bandit with Herding Effects: Algorithms and Recommendation Applicationscited by 1
  5. 2026Direction-Aware Offline-to-Online Learning in Linear Contextual Banditscited by 1
  6. 2022Dual Instrumental Method for Confounded Kernelized Banditscited by 0
  7. 2023Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamicscited by 0
  8. 2024Benchmarks for Reinforcement Learning with Biased Offline Data and Imperfect Simulatorscited by 0
  9. 2025Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicinecited by 0
  10. 2026Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Modelcited by 0