mlsanityData to 14 Oct 2026

CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning

arXiv 2401.16974 ↗First posted 30 Jan 2024cs.LG cs.AIcited by 6

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Causal discovery is the challenging task of inferring causal structure from data. Motivated by Pearl's Causal Hierarchy (PCH), which tells us that passive observations alone are not enough to distinguish correlation from causation, there has been a recent push to incorporate interventions into machine learning research. Reinforcement learning provides a convenient framework for such an active approach to learning. This paper presents CORE, a deep reinforcement learning-based approach for causal discovery and intervention planning. CORE learns to sequentially reconstruct causal graphs from data while learning to perform informative interventions. Our results demonstrate that CORE generalizes to unseen graphs and efficiently uncovers causal structures. Furthermore, CORE scales to larger graphs with up to 10 variables and outperforms existing approaches in structure estimation accuracy and sample efficiency. All relevant code and supplementary material can be found at https://github.com/sa-and/CORE

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 39 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

16 of 39 references.

References · 16

  1. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  2. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 331
  3. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  4. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 211
  5. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  6. 2019Causal Discovery with Reinforcement Learningcited by 145
  7. 2022Amortized Inference for Causal Structure Learningcited by 90
  8. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  9. 2015Learning Causal Graphs with Small Interventionscited by 63
  10. 2021Ordering-Based Causal Discovery with Reinforcement Learningcited by 55
  11. 2022Interventions, Where and How? Experimental Design for Causal Models at Scalecited by 49
  12. 2021Learning Neural Causal Models with Active Interventionscited by 40
4 more
  1. 2019Causal Induction from Visual Observations for Goal Directed Taskscited by 31
  2. 2020Meta Learning for Causal Directioncited by 16
  3. 2022A Meta-Reinforcement Learning Algorithm for Causal Discoverycited by 11
  4. 2022GFlowCausal: Generative Flow Networks for Causal Discoverycited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2024Amortized Active Causal Induction with Deep Reinforcement Learningcited by 10
  2. 2024CausalPlayground: Addressing Data-Generation Requirements in Cutting-Edge Causality Researchcited by 4
  3. 2026Test-Time Learning of Causal Structure from Interventional Datacited by 2
  4. 2025ACTIVA: Amortized Causal Effect Estimation via Transformer-based Variational Autoencodercited by 1
  5. 2025Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problemcited by 1
  6. 2026Active Causal Experimentalist (ACE): Learning Intervention Strategies via Direct Preference Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Reinforcement Learning for Causal Discovery without Acyclicity Constraints
  2. 2025Hierarchical Reinforcement Learning with Targeted Causal Interventions
  3. 2026CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
  4. 2025Causal-Copilot: An Autonomous Causal Analysis Agent
  5. 2026TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
  6. 2024Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization
  7. 2026CauScale: Neural Causal Discovery at Scale
  8. 2025Unifying Causal Reinforcement Learning: Survey, Taxonomy, Algorithms and Applications