# TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfer

arXiv: https://arxiv.org/abs/1907.11200 · HTML: https://mlsanity.com/paper/1907.11200/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2019.

## Built on by (most cited first, 22 of 22)

- [Robot Learning from Randomized Simulations: A Review](https://mlsanity.com/paper/2111.00956/) (2021)
- [Residual Reinforcement Learning from Demonstrations](https://mlsanity.com/paper/2106.08050/) (2021)
- [HuB: Learning Extreme Humanoid Balance](https://mlsanity.com/paper/2505.07294/) (2025)
- [Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning](https://mlsanity.com/paper/2011.01734/) (2020)
- [Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models](https://mlsanity.com/paper/2110.01894/) (2021)
- [AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer](https://mlsanity.com/paper/2302.04903/) (2023)
- [Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation](https://mlsanity.com/paper/2109.08815/) (2021)
- [Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning](https://mlsanity.com/paper/2110.12997/) (2021)
- [Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications](https://mlsanity.com/paper/2410.20357/) (2024)
- [Adapting World Models with Latent-State Dynamics Residuals](https://mlsanity.com/paper/2504.02252/) (2025)
- [Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots](https://mlsanity.com/paper/2303.09597/) (2023)
- [BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning](https://mlsanity.com/paper/2310.10606/) (2023)
- [The Emergence of Deep Reinforcement Learning for Path Planning](https://mlsanity.com/paper/2507.15469/) (2025)
- [Uncertainty Aware System Identification with Universal Policies](https://mlsanity.com/paper/2202.05844/) (2022)
- [Fast Model-based Policy Search for Universal Policy Networks](https://mlsanity.com/paper/2202.05843/) (2022)
- [Zero-shot Sim2Real Adaptation Across Environments](https://mlsanity.com/paper/2302.04013/) (2023)
- [Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfer](https://mlsanity.com/paper/2104.08795/) (2021)
- [Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive Control](https://mlsanity.com/paper/2503.19228/) (2025)
- [PMG: Parameterized Motion Generator for Human-like Locomotion Control](https://mlsanity.com/paper/2602.12656/) (2026)
- [Vid2Sid: Videos Can Help Close the Sim2Real Gap](https://mlsanity.com/paper/2602.19359/) (2026)
- [BEACON: Belief-Enabled Adaptive CONtrol for Imitation Learning under Uncertainty](https://mlsanity.com/paper/2609.22730/) (2026)
- [From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction](https://mlsanity.com/paper/2610.17630/) (2026)

## Abstract (arXiv)

As researchers teach robots to perform more and more complex tasks, the need for realistic simulation environments is growing. Existing techniques for closing the reality gap by approximating real-world physics often require extensive real world data and/or thousands of simulation samples. This paper presents TuneNet, a new machine learning-based method to directly tune the parameters of one model to match another using an *iterative residual tuning* technique. TuneNet estimates the parameter difference between two models using a single observation from the target and minimal simulation, allowing rapid, accurate and sample-efficient parameter estimation. The system can be trained via supervised learning over an auto-generated simulated dataset. We show that TuneNet can perform system identification, even when the true parameter values lie well outside the distribution seen during training, and demonstrate that simulators tuned with TuneNet outperform existing techniques for predicting rigid body motion. Finally, we show that our method can estimate real-world parameter values, allowing a robot to perform sim-to-real task transfer on a dynamic manipulation task unseen during training. Code and videos are available online at http://bit.ly/2lf1bAw.