mlsanityData to 7 Oct 2026

Counterfactual Data Augmentation using Locally Factored Dynamics

arXiv 2007.02863 ↗First posted 6 Jul 2020cs.LG cs.AI cs.ROcited by 93

Not on the map. Why?

Abstract (arXiv)

Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not independent, their interactions are often sparse, and the dynamics at any given time step can often be decomposed into locally independent causal mechanisms. Such local causal structures can be leveraged to improve the sample efficiency of sequence prediction and off-policy reinforcement learning. We formalize this by introducing local causal models (LCMs), which are induced from a global causal model by conditioning on a subset of the state space. We propose an approach to inferring these structures given an object-oriented state representation, as well as a novel algorithm for Counterfactual Data Augmentation (CoDA). CoDA uses local structures and an experience replay to generate counterfactual experiences that are causally valid in the global model. We find that CoDA significantly improves the performance of RL agents in locally factored tasks, including the batch-constrained and goal-conditioned settings.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 9; 2023: 15; 2024: 17; 2025: 23; 2026: 12.

93 papers.

Sort:

By area:

  1. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  2. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  3. 2023HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Datacited by 124
  4. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 104
  5. 2021S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningcited by 85
  6. 2021Causal Influence Detection for Improving Efficiency in Reinforcement Learningcited by 70
  7. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  8. 2021Learning Task Informed Abstractionscited by 58
  9. 2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 48
  10. 2024Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imaginationcited by 45
  11. 2022MoCoDA: Model-based Counterfactual Data Augmentationcited by 44
  12. 2023A Survey on Causal Reinforcement Learningcited by 43
38 more
  1. 2021Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environmentcited by 41
  2. 2022Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoningcited by 33
  3. 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlationcited by 25
  4. 2022Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?cited by 24
  5. 2022Causality-driven Hierarchical Structure Discovery for Reinforcement Learningcited by 23
  6. 2021On Causally Disentangled Representationscited by 22
  7. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  8. 2023Causal Reinforcement Learning: A Surveycited by 22
  9. 2021Counterfactual Temporal Point Processescited by 20
  10. 2021Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domainscited by 18
  11. 2022Variational Causal Dynamics: Discovering Modular World Models from Interventionscited by 16
  12. 2026PlayWorld: Learning Robot World Models from Autonomous Playcited by 16
  13. 2021MapGo: Model-Assisted Policy Optimization for Goal-Oriented Taskscited by 13
  14. 2022Adversarial Counterfactual Environment Model Learningcited by 12
  15. 2024Causal Action Influence Aware Counterfactual Data Augmentationcited by 12
  16. 2024RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrationscited by 12
  17. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  18. 2021Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentationcited by 10
  19. 2021Matching Learned Causal Effects of Neural Networks with Domain Priorscited by 10
  20. 2023Improving Conversational Recommendation Systems via Counterfactual Data Simulationcited by 10
  21. 2023Improving Unsupervised Visual Program Inference with Code Rewriting Familiescited by 10
  22. 2023Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learningcited by 10
  23. 2024Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learningcited by 10
  24. 2024OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learningcited by 10
  25. 2024SPARTAN: A Sparse Transformer World Model Attending to What Matterscited by 10
  26. 2025DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulationcited by 10
  27. 2024Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learningcited by 9
  28. 2024SkiLD: Unsupervised Skill Discovery Guided by Factor Interactionscited by 9
  29. 2021Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentationcited by 8
  30. 2023ELDEN: Exploration via Local Dependenciescited by 8
  31. 2021Causal Learning for Socially Responsible AIcited by 7
  32. 2025MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulationcited by 7
  33. 2023Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updatescited by 6
  34. 2026Factored Latent Action World Modelscited by 6
  35. 2021Counterfactual Maximum Likelihood Estimation for Training Deep Networkscited by 5
  36. 2022Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similaritiescited by 4
  37. 2024On Discovery of Local Independence over Continuous Variables via Neural Contextual Decompositioncited by 4
  38. 2024Variable-Agnostic Causal Exploration for Reinforcement Learningcited by 4

50 most cited of 93 All 93 (JSON)