mlsanityData to 14 Oct 2026

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

arXiv 1710.06537 ↗First posted 18 Oct 2017cs.RO cs.SY eess.SYcited by 672

Not on the map. Why?

Cited by 164 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Simulations are attractive environments for training agents as they provide an abundant source of data and alleviate certain safety concerns during the training process. But the behaviours developed by agents in simulation are often specific to the characteristics of the simulator. Due to modeling error, strategies that are successful in simulation may not transfer to their real world counterparts. In this paper, we demonstrate a simple method to bridge this "reality gap". By randomizing the dynamics of the simulator during training, we are able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained. This adaptivity enables the policies to generalize to the dynamics of the real world without any training on the physical system. Our approach is demonstrated on an object pushing task using a robotic arm. Despite being trained exclusively in simulation, our policies are able to maintain a similar level of performance when deployed on a real robot, reliably moving an object to a desired location from random initial configurations. We explore the impact of various design decisions and show that the resulting policies are robust to significant calibration error.

Key facts. Cited by 672 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 2; 2021: 97; 2022: 108; 2023: 100; 2024: 111; 2025: 107; 2026: 145.

672 papers.

Sort:

By area:

  1. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  2. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 518
  3. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  4. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
  5. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  6. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  7. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  8. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 327
  9. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
  10. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  11. 2023LanguageMPC: Large Language Models as Decision Makers for Autonomous Drivingcited by 190
  12. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
38 more
  1. 2021Maximum Entropy RL (Provably) Solves Some Robust RL Problemscited by 176
  2. 2022Evolving Curricula with Regret-Based Environment Designcited by 173
  3. 2022GNM: A General Navigation Model to Drive Any Robotcited by 171
  4. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  5. 2021Embodied Intelligence via Learning and Evolutioncited by 163
  6. 2023Drive Like a Human: Rethinking Autonomous Driving with Large Language Modelscited by 160
  7. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 151
  8. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 149
  9. 2024Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulationcited by 144
  10. 2021Collaborating with Humans without Human Datacited by 142
  11. 2024Learning Human-to-Humanoid Real-Time Whole-Body Teleoperationcited by 130
  12. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 130
  13. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 126
  14. 2021Goal Misgeneralization in Deep Reinforcement Learningcited by 123
  15. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 116
  16. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 114
  17. 2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 109
  18. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 105
  19. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 99
  20. 2022Robust Reinforcement Learning using Offline Datacited by 96
  21. 2022MetaMorph: Learning Universal Controllers with Transformerscited by 89
  22. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 88
  23. 2019Urban Driving with Conditional Imitation Learningcited by 86
  24. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  25. 2022A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learningcited by 83
  26. 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 83
  27. 2023Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulationcited by 82
  28. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 82
  29. 2024Robust agents learn causal world modelscited by 81
  30. 2021Understanding Domain Randomization for Sim-to-real Transfercited by 80
  31. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 71
  32. 2022CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learningcited by 71
  33. 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 70
  34. 2022A Survey on Model-based Reinforcement Learningcited by 66
  35. 2021Robot Learning from Randomized Simulations: A Reviewcited by 63
  36. 2022When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learningcited by 60
  37. 2022Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learningcited by 60
  38. 2023TorchRL: A data-driven decision-making library for PyTorchcited by 60

50 most cited of 672 All 672 (JSON)