mlsanityData to 7 Oct 2026

BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators

arXiv 1906.01728 ↗First posted 4 Jun 2019cs.RO cs.LGcited by 78

Not on the map. Why?

Abstract (arXiv)

We introduce BayesSim, a framework for robotics simulations allowing a full Bayesian treatment for the parameters of the simulator. As simulators become more sophisticated and able to represent the dynamics more accurately, fundamental problems in robotics such as motion planning and perception can be solved in simulation and solutions transferred to the physical robot. However, even the most complex simulator might still not be able to represent reality in all its details either due to inaccurate parametrization or simplistic assumptions in the dynamic models. BayesSim provides a principled framework to reason about the uncertainty of simulation parameters. Given a black box simulator (or generative model) that outputs trajectories of state and action pairs from unknown simulation parameters, followed by trajectories obtained with a physical robot, we develop a likelihood-free inference method that computes the posterior distribution of simulation parameters. This posterior can then be used in problems where Sim2Real is critical, for example in policy search. We compare the performance of BayesSim in obtaining accurate posteriors in a number of classical control and robotics problems. Results show that the posterior computed from BayesSim can be used for domain randomization outperforming alternative methods that randomize based on uniform priors.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 15; 2022: 17; 2023: 11; 2024: 9; 2025: 14; 2026: 11.

78 papers.

Sort:

By area:

  1. 2023GenSim: Generating Robotic Simulation Tasks via Large Language Modelscited by 120
  2. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 104
  3. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 101
  4. 2021gradSim: Differentiable simulation for system identification and visuomotor controlcited by 100
  5. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 80
  6. 2024DrEureka: Language Model Guided Sim-To-Real Transfercited by 78
  7. 2022Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learningcited by 58
  8. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  9. 2024GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMscited by 48
  10. 2022Visual Reinforcement Learning with Self-Supervised 3D Representationscited by 45
  11. 2025Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulationcited by 42
  12. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
38 more
  1. 2021Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFingercited by 34
  2. 2023Cross-Domain Policy Adaptation via Value-Guided Data Filteringcited by 30
  3. 2022DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objectscited by 29
  4. 2020Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learningcited by 27
  5. 2024ASID: Active Exploration for System Identification in Robotic Manipulationcited by 27
  6. 2024ODRL: A Benchmark for Off-Dynamics Reinforcement Learningcited by 25
  7. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 24
  8. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 24
  9. 2025The Reality Gap in Robotics: Challenges, Solutions, and Best Practicescited by 22
  10. 2021Value Iteration in Continuous Actions, States and Timecited by 17
  11. 2021Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulationcited by 17
  12. 2023AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfercited by 17
  13. 2023Adversarial robustness of amortized Bayesian inferencecited by 17
  14. 2022DROPO: Sim-to-Real Transfer with Offline Domain Randomizationcited by 16
  15. 2024A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agentscited by 16
  16. 2023MoVie: Visual Model-Based Policy Adaptation for View Generalizationcited by 15
  17. 2023H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gapscited by 15
  18. 2025Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuningcited by 15
  19. 2021A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulationcited by 11
  20. 2024The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learningcited by 11
  21. 2021Dual Online Stein Variational Inference for Control and Dynamicscited by 10
  22. 2022Policy Adaptation from Foundation Model Feedbackcited by 10
  23. 2024Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identificationscited by 10
  24. 2024Robot Learning with Super-Linear Scalingcited by 10
  25. 2025OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learningcited by 10
  26. 2021Robust Value Iteration for Continuous Control Taskscited by 8
  27. 2021OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulationcited by 7
  28. 2022Weakly Supervised Correspondence Learningcited by 7
  29. 2022Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomizationcited by 7
  30. 2026ContactGaussian-WM: Learning Physics-Grounded World Model from Videoscited by 7
  31. 2021Sim and Real: Better Togethercited by 6
  32. 2021Continuous-Time Fitted Value Iteration for Robust Policiescited by 6
  33. 2022DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cuttingcited by 6
  34. 2022Real2Sim2Real Transfer for Control of Cable-driven Robots via a Differentiable Physics Enginecited by 5
  35. 2022Online vs. Offline Adaptive Domain Randomization Benchmarkcited by 4
  36. 2023Fine-Tuning Generative Models as an Inference Method for Robotic Taskscited by 4
  37. 2025Flow-based Domain Randomization for Learning and Sequencing Robotic Skillscited by 4
  38. 2021BayesSimIG: Scalable Parameter Inference for Adaptive Domain Randomization with IsaacGymcited by 3

50 most cited of 78 All 78 (JSON)