# Intervention Design for Effective Sim2Real Transfer

arXiv: https://arxiv.org/abs/2012.02055 · HTML: https://mlsanity.com/paper/2012.02055/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [Causal Dynamics Learning for Task-Independent State Abstraction](https://mlsanity.com/paper/2206.13452/) (2022)
- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2206.04551/) (2022)
- [Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization](https://mlsanity.com/paper/2209.01121/) (2022)
- [Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond](https://mlsanity.com/paper/2202.14034/) (2022)
- [VIBR: Learning View-Invariant Value Functions for Robust Visual Control](https://mlsanity.com/paper/2306.08537/) (2023)
- [Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agent](https://mlsanity.com/paper/2501.14443/) (2025)

## Abstract (arXiv)

The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting. We explain this success through the lens of causal inference, positioning domain randomization and data augmentation as interventions on the environment which encourage invariance to irrelevant features. Such interventions include visual perturbations that have no effect on reward and dynamics. This encourages the learning algorithm to be robust to these types of variations and learn to attend to the true causal mechanisms for solving the task. This connection leads to two key findings: (1) perturbations to the environment do not have to be realistic, but merely show variation along dimensions that also vary in the real world, and (2) use of an explicit invariance-inducing objective improves generalization in sim2sim and sim2real transfer settings over just data augmentation or domain randomization alone. We demonstrate the capability of our method by performing zero-shot transfer of a robot arm reach task on a 7DoF Jaco arm learning from pixel observations.