# Counterfactual Data Augmentation using Locally Factored Dynamics

arXiv: https://arxiv.org/abs/2007.02863 · HTML: https://mlsanity.com/paper/2007.02863/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 30 of 93)

- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Pseudo-Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.04218/) (2025)
- [HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data](https://mlsanity.com/paper/2311.13614/) (2023)
- [DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning](https://mlsanity.com/paper/2410.24185/) (2024)
- [S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning](https://mlsanity.com/paper/2103.06326/) (2021)
- [Causal Influence Detection for Improving Efficiency in Reinforcement Learning](https://mlsanity.com/paper/2106.03443/) (2021)
- [Learning from Counterfactual Links for Link Prediction](https://mlsanity.com/paper/2106.02172/) (2021)
- [Learning Task Informed Abstractions](https://mlsanity.com/paper/2106.15612/) (2021)
- [SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment](https://mlsanity.com/paper/2410.18907/) (2024)
- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination](https://mlsanity.com/paper/2412.14957/) (2024)
- [MoCoDA: Model-based Counterfactual Data Augmentation](https://mlsanity.com/paper/2210.11287/) (2022)
- [Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment](https://mlsanity.com/paper/2104.05632/) (2021)
- [Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning](https://mlsanity.com/paper/2207.09081/) (2022)
- [Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation](https://mlsanity.com/paper/2307.07907/) (2023)
- [Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?](https://mlsanity.com/paper/2206.05266/) (2022)
- [Causality-driven Hierarchical Structure Discovery for Reinforcement Learning](https://mlsanity.com/paper/2210.06964/) (2022)
- [Causal Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.01452/) (2023)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Counterfactual Learning on Graphs: A Survey](https://mlsanity.com/paper/2304.01391/) (2023)
- [Counterfactual Temporal Point Processes](https://mlsanity.com/paper/2111.07603/) (2021)
- [Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains](https://mlsanity.com/paper/2110.15949/) (2021)
- [PlayWorld: Learning Robot World Models from Autonomous Play](https://mlsanity.com/paper/2603.09030/) (2026)
- [Variational Causal Dynamics: Discovering Modular World Models from Interventions](https://mlsanity.com/paper/2206.11131/) (2022)
- [MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks](https://mlsanity.com/paper/2105.06350/) (2021)
- [RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations](https://mlsanity.com/paper/2411.16959/) (2024)
- [Adversarial Counterfactual Environment Model Learning](https://mlsanity.com/paper/2206.04890/) (2022)
- [Causal Action Influence Aware Counterfactual Data Augmentation](https://mlsanity.com/paper/2405.18917/) (2024)
- [Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning](https://mlsanity.com/paper/2406.03234/) (2024)
- [DemoHLM: From One Demonstration to Generalizable Humanoid Loco-Manipulation](https://mlsanity.com/paper/2510.11258/) (2025)

## 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.