# Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics

arXiv: https://arxiv.org/abs/2008.06686 · HTML: https://mlsanity.com/paper/2008.06686/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2020.

## Built on by (most cited first, 21 of 21)

- [Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16470/) (2021)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [DROPO: Sim-to-Real Transfer with Offline Domain Randomization](https://mlsanity.com/paper/2201.08434/) (2022)
- [Domain Randomization via Entropy Maximization](https://mlsanity.com/paper/2311.01885/) (2023)
- [Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization](https://mlsanity.com/paper/2209.12878/) (2022)
- [Dual Online Stein Variational Inference for Control and Dynamics](https://mlsanity.com/paper/2103.12890/) (2021)
- [Coarse-to-Fine for Sim-to-Real: Sub-Millimetre Precision Across Wide Task Spaces](https://mlsanity.com/paper/2105.11283/) (2021)
- [Learning Eye-in-Hand Camera Calibration from a Single Image](https://mlsanity.com/paper/2111.01245/) (2021)
- [Robust Visual Sim-to-Real Transfer for Robotic Manipulation](https://mlsanity.com/paper/2307.15320/) (2023)
- [Flow-based Domain Randomization for Learning and Sequencing Robotic Skills](https://mlsanity.com/paper/2502.01800/) (2025)
- [Roll-Drop: accounting for observation noise with a single parameter](https://mlsanity.com/paper/2304.13150/) (2023)
- [Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics](https://mlsanity.com/paper/2503.10949/) (2025)
- [Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation](https://mlsanity.com/paper/2103.07223/) (2021)
- [Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report](https://mlsanity.com/paper/2404.04106/) (2024)
- [Shaping Laser Pulses with Reinforcement Learning](https://mlsanity.com/paper/2503.00499/) (2025)
- [Mechanical Intelligence-Aware Curriculum Reinforcement Learning for Humanoids with Parallel Actuation](https://mlsanity.com/paper/2507.00273/) (2025)
- [The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective](https://mlsanity.com/paper/2606.07017/) (2026)
- [Variable-Friction In-Hand Manipulation for Arbitrary Objects via Diffusion-Based Imitation Learning](https://mlsanity.com/paper/2503.02738/) (2025)
- [Direct transfer of optimized controllers to similar systems using dimensionless MPC](https://mlsanity.com/paper/2512.08667/) (2025)
- [Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection](https://mlsanity.com/paper/2603.21853/) (2026)
- [How Should a Simulation-to-Reality Transfer Budget Be Spent?](https://mlsanity.com/paper/2606.22062/) (2026)

## Abstract (arXiv)

Zero-shot sim-to-real transfer of tasks with complex dynamics is a highly challenging and unsolved problem. A number of solutions have been proposed in recent years, but we have found that many works do not present a thorough evaluation in the real world, or underplay the significant engineering effort and task-specific fine tuning that is required to achieve the published results. In this paper, we dive deeper into the sim-to-real transfer challenge, investigate why this is such a difficult problem, and present objective evaluations of a number of transfer methods across a range of real-world tasks. Surprisingly, we found that a method which simply injects random forces into the simulation performs just as well as more complex methods, such as those which randomise the simulator's dynamics parameters, or adapt a policy online using recurrent network architectures.