mlsanityData to 7 Oct 2026

Budgeted and Non-budgeted Causal Bandits

arXiv 2012.07058 ↗First posted 13 Dec 2020cs.LG stat.MLcited by 38

Not on the map. Why?

Abstract (arXiv)

Learning good interventions in a causal graph can be modelled as a stochastic multi-armed bandit problem with side-information. First, we study this problem when interventions are more expensive than observations and a budget is specified. If there are no backdoor paths from an intervenable node to the reward node then we propose an algorithm to minimize simple regret that optimally trades-off observations and interventions based on the cost of intervention. We also propose an algorithm that accounts for the cost of interventions, utilizes causal side-information, and minimizes the expected cumulative regret without exceeding the budget. Our cumulative-regret minimization algorithm performs better than standard algorithms that do not take side-information into account. Finally, we study the problem of learning best interventions without budget constraint in general graphs and give an algorithm that achieves constant expected cumulative regret in terms of the instance parameters when the parent distribution of the reward variable for each intervention is known. Our results are experimentally validated and compared to the best-known bounds in the current literature.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 7; 2023: 11; 2024: 10; 2025: 3; 2026: 2.

38 papers.

Sort:

  1. 2022Causal Structure Learning: a Combinatorial Perspectivecited by 46
  2. 2023A Survey on Causal Reinforcement Learningcited by 43
  3. 2021Causal Bandits with Unknown Graph Structurecited by 37
  4. 2023Causal Reinforcement Learning: A Surveycited by 22
  5. 2023Causal Deep Learningcited by 20
  6. 2022Causal Bandits for Linear Structural Equation Modelscited by 19
  7. 2022Adaptively Exploiting d-Separators with Causal Banditscited by 18
  8. 2022Combinatorial Causal Banditscited by 16
  9. 2021A Causal Bandit Approach to Learning Good Atomic Interventions in Presence of Unobserved Confounderscited by 15
  10. 2021Bandit Algorithms for Precision Medicinecited by 12
  11. 2023Causal Bandits without Graph Learningcited by 10
  12. 2023Additive Causal Bandits with Unknown Graphcited by 10
26 more
  1. 2022Combinatorial Pure Exploration of Causal Banditscited by 9
  2. 2021Causal Markov Decision Processes: Learning Good Interventions Efficientlycited by 7
  3. 2022Sample Constrained Treatment Effect Estimationcited by 7
  4. 2023Combinatorial Causal Bandits without Graph Skeletoncited by 7
  5. 2024Causal Bandits with General Causal Models and Interventionscited by 7
  6. 2023Learning Good Interventions in Causal Graphs via Coveringcited by 5
  7. 2023Functional Causal Bayesian Optimizationcited by 5
  8. 2023Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learningcited by 5
  9. 2024Causally Abstracted Multi-armed Banditscited by 5
  10. 2024Linear Causal Bandits: Unknown Graph and Soft Interventionscited by 5
  11. 2024Partial Structure Discovery is Sufficient for No-regret Learning in Causal Banditscited by 5
  12. 2023Robust Causal Bandits for Linear Modelscited by 4
  13. 2024Confounded Budgeted Causal Banditscited by 4
  14. 2022Uplifting Banditscited by 2
  15. 2024Improved Bound for Robust Causal Bandits with Linear Modelscited by 2
  16. 2024Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginalscited by 2
  17. 2024Asymmetric Graph Error Control with Low Complexity in Causal Banditscited by 2
  18. 2025Graph Learning Is Suboptimal in Causal Banditscited by 2
  19. 2021Intervention Efficient Algorithm for Two-Stage Causal MDPscited by 1
  20. 2024Causal Contextual Bandits with Adaptive Contextcited by 1
  21. 2024The Importance of Causality in Decision Making: A Perspective on Recommender Systemscited by 1
  22. 2025Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustmentcited by 1
  23. 2025The Minimal Search Space for Conditional Causal Banditscited by 1
  24. 2023Optimal Observation-Intervention Trade-Off in Optimisation Problems with Causal Structurecited by 0
  25. 2026Integrating Causal DAGs in Deep RL: Activating Minimal Markovian States with Multi-Order Exposurecited by 0
  26. 2026Active Context Selection Improves Simple Regret in Contextual Banditscited by 0