# What Went Wrong? Closing the Sim-to-Real Gap via Differentiable Causal Discovery

arXiv: https://arxiv.org/abs/2306.15864 · HTML: https://mlsanity.com/paper/2306.15864/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2023.

## Built on by (most cited first, 27 of 27)

- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Open-Endedness is Essential for Artificial Superhuman Intelligence](https://mlsanity.com/paper/2406.04268/) (2024)
- [A Survey on Robotics with Foundation Models: toward Embodied AI](https://mlsanity.com/paper/2402.02385/) (2024)
- [AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World](https://mlsanity.com/paper/2503.24278/) (2025)
- [Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/2503.24361/) (2025)
- [Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination](https://mlsanity.com/paper/2412.14957/) (2024)
- [ASID: Active Exploration for System Identification in Robotic Manipulation](https://mlsanity.com/paper/2404.12308/) (2024)
- [The Reality Gap in Robotics: Challenges, Solutions, and Best Practices](https://mlsanity.com/paper/2510.20808/) (2025)
- [Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning](https://mlsanity.com/paper/2502.02705/) (2025)
- [Learning rigid-body simulators over implicit shapes for large-scale scenes and vision](https://mlsanity.com/paper/2405.14045/) (2024)
- [CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories](https://mlsanity.com/paper/2403.13208/) (2024)
- [Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications](https://mlsanity.com/paper/2410.20357/) (2024)
- [Continual Domain Randomization](https://mlsanity.com/paper/2403.12193/) (2024)
- [Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids](https://mlsanity.com/paper/2508.12252/) (2025)
- [Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning](https://mlsanity.com/paper/2405.03113/) (2024)
- [SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training](https://mlsanity.com/paper/2507.04452/) (2025)
- [House of Dextra: Cross-embodied Co-design for Dexterous Hands](https://mlsanity.com/paper/2512.03743/) (2025)
- [LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrations](https://mlsanity.com/paper/2508.17547/) (2025)
- [BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning](https://mlsanity.com/paper/2407.10967/) (2024)
- [Your Learned Constraint is Secretly a Backward Reachable Tube](https://mlsanity.com/paper/2501.15618/) (2025)
- [Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation](https://mlsanity.com/paper/2503.11731/) (2025)
- [Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics](https://mlsanity.com/paper/2503.10949/) (2025)
- [Learning Robust Policies via Interpretable Hamilton-Jacobi Reachability-Guided Disturbances](https://mlsanity.com/paper/2409.19746/) (2024)
- [Neural Fidelity Calibration for Informative Sim-to-Real Adaptation](https://mlsanity.com/paper/2504.08604/) (2025)
- [Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Picking](https://mlsanity.com/paper/2504.15414/) (2025)
- [Robot Pouring: Identifying Causes of Spillage and Selecting Alternative Action Parameters Using Probabilistic Actual Causation](https://mlsanity.com/paper/2502.09395/) (2025)
- [Abstract Sim2Real through Approximate Information States](https://mlsanity.com/paper/2604.15289/) (2026)

## Abstract (arXiv)

Training control policies in simulation is more appealing than on real robots directly, as it allows for exploring diverse states in an efficient manner. Yet, robot simulators inevitably exhibit disparities from the real-world rebutdynamics, yielding inaccuracies that manifest as the dynamical simulation-to-reality (sim-to-real) gap. Existing literature has proposed to close this gap by actively modifying specific simulator parameters to align the simulated data with real-world observations. However, the set of tunable parameters is usually manually selected to reduce the search space in a case-by-case manner, which is hard to scale up for complex systems and requires extensive domain knowledge. To address the scalability issue and automate the parameter-tuning process, we introduce COMPASS, which aligns the simulator with the real world by discovering the causal relationship between the environment parameters and the sim-to-real gap. Concretely, our method learns a differentiable mapping from the environment parameters to the differences between simulated and real-world robot-object trajectories. This mapping is governed by a simultaneously learned causal graph to help prune the search space of parameters, provide better interpretability, and improve generalization on unseen parameters. We perform experiments to achieve both sim-to-sim and sim-to-real transfer, and show that our method has significant improvements in trajectory alignment and task success rate over strong baselines in several challenging manipulation tasks.