mlsanityData to 7 Oct 2026

Bridging the Sim-to-Real Gap with Bayesian Inference

arXiv 2403.16644 ↗First posted 25 Mar 2024cs.RO cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We present SIM-FSVGD for learning robot dynamics from data. As opposed to traditional methods, SIM-FSVGD leverages low-fidelity physical priors, e.g., in the form of simulators, to regularize the training of neural network models. While learning accurate dynamics already in the low data regime, SIM-FSVGD scales and excels also when more data is available. We empirically show that learning with implicit physical priors results in accurate mean model estimation as well as precise uncertainty quantification. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system. Using model-based RL, we demonstrate a highly dynamic parking maneuver with drifting, using less than half the data compared to the state of the art.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 33 of its 57 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

33 of 57 references.

References · 33

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  7. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  8. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  9. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  10. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  11. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  12. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
21 more
  1. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  2. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  3. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  4. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  5. 2020Bayesian Neural Networks: An Introduction and Surveycited by 130
  6. 2019Functional Variational Bayesian Neural Networkscited by 127
  7. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  8. 2020Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planningcited by 83
  9. 2018A Spectral Approach to Gradient Estimation for Implicit Distributionscited by 45
  10. 2018A Unified Particle-Optimization Framework for Scalable Bayesian Samplingcited by 44
  11. 2019Function Space Particle Optimization for Bayesian Neural Networkscited by 41
  12. 2023Optimistic Active Exploration of Dynamical Systemscited by 32
  13. 2019AMZ Driverless: The Full Autonomous Racing Systemcited by 28
  14. 2020Nonparametric Score Estimatorscited by 22
  15. 2023Efficient Exploration in Continuous-time Model-based Reinforcement Learningcited by 21
  16. 2023Hallucinated Adversarial Control for Conservative Offline Policy Evaluationcited by 13
  17. 2023Tuning Legged Locomotion Controllers via Safe Bayesian Optimizationcited by 8
  18. 2022Gradient-Based Trajectory Optimization With Learned Dynamicscited by 7
  19. 2023Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learningcited by 6
  20. 2017Fast Model Identification via Physics Engines for Data-Efficient Policy Searchcited by 5
  21. 2022Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse Data using a Learning-based Unscented Kalman Filtercited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025SOMBRL: Scalable and Optimistic Model-Based RLcited by 7
  2. 2025Sample-efficient and Scalable Exploration in Continuous-Time RLcited by 3
  3. 2025Learning Soft Robotic Dynamics with Active Explorationcited by 2
  4. 2026Model-Based Reinforcement Learning for Control under Time-Varying Dynamicscited by 1
  5. 2025Distributed Risk-Sensitive Safety Filters for Uncertain Discrete-Time Systemscited by 0
  6. 2025TARC: Time-Adaptive Robotic Controlcited by 0