Domain Randomization

Follow this topic Ask about this topic

Domain randomization studies how to train models on varied simulated or synthetic conditions so they generalize to real settings that differ from training data. Common approaches randomize physics and controller parameters for reinforcement-learning policies, vary appearance through procedural rendering or generative image augmentation, and use staged curricula or online adaptation. Researchers test these methods in sim-to-real robot control and manipulation, as well as out-of-domain medical imaging and industrial object recognition, using both perturbation benchmarks and physical systems. A central tension is how to choose useful variation: broader randomization can improve robustness, but may waste training effort or underperform targeted system identification, realistic modeling, and carefully ordered curricula.

Latest papers

24 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

When Does Dynamics Randomization Test Context Inference?
Oct 23, 2026Oleg Smirnov, Sofiane Ennadir, John Pertoft +2Contextual RL Reinforcement Learning
King AI Labs, Microsoft Gaming · King AI Labs, Microsoft Gaming & KTH Royal Institute of Technology
Delay Randomization Widens the Delay Margin of Learned Humanoid Motion Trackers
Oct 23, 2026Shaoqin Li, Yi SunHumanoid Robot Control Robust Control
Department of Electrical Engineering, The City College of New York, New York, NY 10031, USA
ReSeg: Retraining-free segmentation of abdominal organs via generalizable semantic representation learning
Oct 21, 2026Derong Yu, Guoyan ZhengZero-Shot Medical Image Segmentation Domain Generalization for Semantic Segmentation
Institute of Medical Robotics, School of Biomedical Engineering, Shanghai Jiao Tong University, No.800 Dongchuan Road, Shanghai, 200240, China
Memorize, Adapt, Ignore: Diagnosing Robot Learning Mechanisms under Training Data Variation
Sep 29, 2026Ke Zhang, Danica J. Sutherland, Chao LiuDomain Randomization Robot Policy Adaptation
PRIME Robotics Lab, Department of Mechanical Engineering, The University of British Columbia · Department of Computer Science, University of British Columbia · Alberta Machine Intelligence Institute
AxonSynth: Domain-Randomized Synthetic Data for Zero-Shot 3D Axon Segmentation in Light-Sheet Microscopy
Sep 25, 2026Edward Gaibor, Kyriaki-Margarita Bintsi, Chiara Mauri +9Domain Randomization Synthetic-to-Real Domain Adaptation
Department of Computer Science, University of Massachusetts Boston, Boston, MA, USA · Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Charlestown, MA, USA · Universidad San Sebastián, Chile +4
Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes
Sep 22, 2026Jose Moises Araya-Martinez, Gautham Mohan, Jens LambrechtDomain Randomization Synthetic Data Augmentation
Electrical Engineering and Computer Science TU Berlin Berlin, Germany · Electrical Engineering University of Stuttgart Stuttgart, Germany · Institute for Cognitive Robotics TU Braunschweig Braunschweig, Germany
ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning
Sep 17, 2026Chiyoung Kim, Min Sung Choi, Jinho Ju +5Domain Randomization Visuomotor Policy Learning
Chung-Ang University, Seoul, Republic of Korea
Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control
Sep 9, 2026Xun HuangQuadrotor Control Robust RL
State Key Laboratory of Turbulence and Complex Systems, Department of Aeronautics and Astronautics, Peking University, Beijing, 100871, People’s Republic of China
Generalizing HVAC Control With Domain Randomized Reinforcement Learning
Sep 5, 2026Pablo Boitel, Kun ZhangHeating, Ventilation, and Air Conditioning Control RL Control
École de technologie supérieure (ÉTS) Montréal, Québec, Canada
Meshless Domain Randomization via Explicit Parameter Perturbation of 3D Gaussian Splatting
Jul 24, 2026Felipe Nunes Carbone de Carvalho, Joyce de Morais Souza, Alan de Aguiar +2Domain Randomization 3D Gaussian Splatting
Federal University of ABC (UFABC), Santo Andr´e, Brazil
Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints
Jul 19, 2026Hany Hamed, Abhishek Naik, Colin Bellinger +1Domain Randomization Reinforcement Learning
University of Alberta · 3Alberta Machine Intelligence Institute (Amii) · 7Generative Bionics +4
How Should a Simulation-to-Reality Transfer Budget Be Spent?
Jun 20, 2026Syed Hamzah Rizvi, Yash Vardhan TomarRobot Dynamics Identification Domain Randomization
Purdue University West Lafayette, USA
HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling
Jun 3, 2026Chenhao Bai, Liqin Lu, Kaijun Wang +5Domain Randomization Curriculum RL
1Zhejiang University, State Key Lab of CAD & CG · 2Zhejiang University of Technology
When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
May 12, 2026Xiaolin Zhou, Aojie Yuan, Zheng Luo +12Domain Randomization AI Agent Benchmarks
Arizona State University · University of Southern California · University of Pennsylvania +2
Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching
May 10, 2026Kejia Ren, Gaotian Wang, Andrew S. Morgan +1Domain Randomization Robot Skill Learning
Department of Computer Science, Rice University · Robotics and AI Institute
On Surprising Effects of Risk-Aware Domain Randomization for Contact-Rich Sampling-based Predictive Control
May 5, 2026Sergio A. Esteban, Junheng Li, Vince Kurtz +1Domain Randomization Contact-Rich Manipulation
Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, CA, USA · School of Computing, DePaul University, Chicago, IL, USA
SIAM: Head and Brain MRI Segmentation from Few High-Quality Templates via Synthetic Training
May 4, 2026Romain Valabregue, Ines Khemir, Eric Badinet +3Domain Randomization Medical Image Segmentation
Sorbonne Universit´e, Institut du Cerveau - Paris Brain Institute ICM, CNRS, Inria, Inserm, AP-HP, Hˆopital de la Piti´e Salpˆetri`ere, F-75013, Paris, France · IMT Atlantique, LaTIM INSERM U1101, Brest, France · Aix-Marseille Universit´e, CNRS, Institut de Neurosciences de la Timone, UMR 7289, Marseille, France
DexSim2Real: Foundation Model-Guided Sim-to-Real Transfer for Generalizable Dexterous Manipulation
May 3, 2026Zijian Zeng, Fei Ding, Huiming Yang +2Domain Randomization Dexterous Manipulation
Tsinghua University · Alibaba Group · Bengbu University +1
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models
Apr 15, 2026Yangyue Wang, Harshvardhan Sikka, Yash Mathur +3VLM Evaluation Domain Randomization
1Fig · 2Manifold Research
ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
Apr 13, 2026Arjun Bhardwaj, Maximum Wilder-Smith, Mayank Mittal +2Robotic Manipulation Dexterous Manipulation
ETH Zurich · NVIDIA
Grounding Sim-to-Real Generalization in Robotic Manipulation: An Empirical Study with Vision-Language-Action Models
Mar 24, 2026Ruixing Jin, Zicheng Zhu, Ruixiang Ouyang +4Domain Randomization Robotics Simulation
School of Data Science, The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute
SynthRender and I-AsSET: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception
Feb 24, 2026Jose Moises Araya-Martinez, Thushar Tom, Adrián Sanchis Reig +3Sim-to-Real Transfer Synthetic-to-Real Domain Adaptation
Technical University Berlin, Industrial Automation Technology, Berlin, Germany · Mercedes-Benz AG, Future Manufacturing Technologies, Sindelfingen, Germany · Technical University Braunschweig, Institute for Cognitive Robotics, Braunschweig, Germany
Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies
Oct 8, 2025David Rytz, Kim Tien Ly, Ioannis HavoutisDomain Randomization Sim-to-Real Transfer
1Dynamic Robot Systems, Oxford Robotics Institute, University of Oxford
Evaluating Synthetic Data Generation for Domain Generalization in Fetal Brain MRI Segmentation
Nov 11, 2024Vladyslav Zalevskyi, Thomas Sanchez, Margaux Roulet +10Domain Randomization Cross-Modality Medical Image Segmentation
Department of Radiology, Lausanne University Hospital and University of Lausanne (UNIL), Lausanne, Switzerland · CIBM Center for Biomedical Imaging, Lausanne, Switzerland · Institute for Information Processing, Leibniz University Hannover, Hannover, Germany +5

Oct 23, 2026J/K move · Enter open · S save

When Does Dynamics Randomization Test Context Inference?

Oleg Smirnov, Sofiane Ennadir, John Pertoft, Bjartur Hjaltason+1

King AI Labs, Microsoft Gaming · King AI Labs, Microsoft Gaming & KTH Royal Institute of Technology

Contextual RL Reinforcement Learning Domain Randomization Action-Conditioned World Models

Open paper AskPDF arXiv

Environments with randomized dynamics are widely used to ask whether world models need explicit context inference. However, randomization can leave little predictive information for a context encoder to add, because distinct latent parameters may produce similar transitions at visited states, or those states may already reveal the active context. We formalize the remaining one-step information as predictive headroom and compare kernels under fixed and visited state--action distributions to distinguish changes in query coverage from changes in context weights. We analyze discrete and continuous environments and find low headroom both when kernels differ little and when visitation reduces an otherwise large discrepancy. At the same time, resetting state components increases headroom, showing that context evidence accumulates in state. We propose reporting this headroom alongside the randomized parameters, so that gains from explicit context inference can be interpreted relative to the information missing from the current state and action.