mlsanityData to 7 Oct 2026

Causal Bandits without Graph Learning

arXiv 2301.11401 ↗First posted 26 Jan 2023stat.ML cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

We study the causal bandit problem when the causal graph is unknown and develop an efficient algorithm for finding the parent node of the reward node using atomic interventions. We derive the exact equation for the expected number of interventions performed by the algorithm and show that under certain graphical conditions it could perform either logarithmically fast or, under more general assumptions, slower but still sublinearly in the number of variables. We formally show that our algorithm is optimal as it meets the universal lower bound we establish for any algorithm that performs atomic interventions. Finally, we extend our algorithm to the case when the reward node has multiple parents. Using this algorithm together with a standard algorithm from bandit literature leads to improved regret bounds.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 9 of its 30 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

9 of 30 references.

References · 9

  1. 2016Causal Bandits: Learning Good Interventions via Causal Inferencecited by 100
  2. 2015Learning Causal Graphs with Small Interventionscited by 63
  3. 2017Identifying Best Interventions through Online Importance Samplingcited by 39
  4. 2020Active Structure Learning of Causal DAGs via Directed Clique Treecited by 38
  5. 2020Budgeted and Non-budgeted Causal Banditscited by 38
  6. 2021Causal Bandits with Unknown Graph Structurecited by 37
  7. 2018Contextual Multi-Armed Bandits for Causal Marketingcited by 17
  8. 2020Causal Bandits without prior knowledge using separating setscited by 17
  9. 2021Learning Bayesian Networks in the Presence of Structural Side Informationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 2; 2026: 1.

10 papers.

  1. 2023Combinatorial Causal Bandits without Graph Skeletoncited by 7
  2. 2024Causal Bandits with General Causal Models and Interventionscited by 7
  3. 2024Linear Causal Bandits: Unknown Graph and Soft Interventionscited by 5
  4. 2024Partial Structure Discovery is Sufficient for No-regret Learning in Causal Banditscited by 5
  5. 2023Robust Causal Bandits for Linear Modelscited by 4
  6. 2024Improved Bound for Robust Causal Bandits with Linear Modelscited by 2
  7. 2025Graph Learning Is Suboptimal in Causal Banditscited by 2
  8. 2024Graph Agnostic Causal Bayesian Optimisationcited by 1
  9. 2025Causal Bandit Over Unknown Graphs: Upper Confidence Bounds With Backdoor Adjustmentcited by 1
  10. 2026Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signalscited by 0