mlsanityData to 14 Oct 2026

Simulation Priors for Data-Efficient Deep Learning

arXiv 2509.05732 ↗First posted 6 Sep 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

How do we enable AI systems to efficiently learn in the real-world? First-principles models are widely used to simulate natural systems, but often fail to capture real-world complexity due to simplifying assumptions. In contrast, deep learning approaches can estimate complex dynamics with minimal assumptions but require large, representative datasets. We propose SimPEL, a method that efficiently combines first-principles models with data-driven learning by using low-fidelity simulators as priors in Bayesian deep learning. This enables SimPEL to benefit from simulator knowledge in low-data regimes and leverage deep learning's flexibility when more data is available, all the while carefully quantifying epistemic uncertainty. We evaluate SimPEL on diverse systems, including biological, agricultural, and robotic domains, showing superior performance in learning complex dynamics. For decision-making, we demonstrate that SimPEL bridges the sim-to-real gap in model-based reinforcement learning. On a high-speed RC car task, SimPEL learns a highly dynamic parking maneuver involving drifting with substantially less data than state-of-the-art baselines. These results highlight the potential of SimPEL for data-efficient learning and control in complex real-world environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 80 references that are in the map. First posted on arXiv 6 Sep 2025.

Builds on

46 of 80 references.

References · 46

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  6. 2016Variational Inference: A Review for Statisticianscited by 1,472
  7. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  8. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  9. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  10. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  11. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  12. 2020dm_control: Software and Tasks for Continuous Controlcited by 375
34 more
  1. 2020Planning to Explore via Self-Supervised World Modelscited by 368
  2. 2018SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inferencecited by 333
  3. 2018Gaussian Process Behaviour in Wide Deep Neural Networkscited by 317
  4. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
  5. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  6. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 246
  7. 2019Active Domain Randomizationcited by 170
  8. 2020Bayesian Neural Networks: An Introduction and Surveycited by 131
  9. 2019Functional Variational Bayesian Neural Networkscited by 127
  10. 2021Repulsive Deep Ensembles are Bayesiancited by 104
  11. 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 101
  12. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  13. 2020Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planningcited by 86
  14. 2021Understanding Domain Randomization for Sim-to-real Transfercited by 80
  15. 2020All You Need is a Good Functional Prior for Bayesian Deep Learningcited by 61
  16. 2018A Spectral Approach to Gradient Estimation for Implicit Distributionscited by 45
  17. 2018A Unified Particle-Optimization Framework for Scalable Bayesian Samplingcited by 44
  18. 2019Function Space Particle Optimization for Bayesian Neural Networkscited by 41
  19. 2014Avoiding pathologies in very deep networkscited by 33
  20. 2023Optimistic Active Exploration of Dynamical Systemscited by 32
  21. 2019AMZ Driverless: The Full Autonomous Racing Systemcited by 29
  22. 2021Precise characterization of the prior predictive distribution of deep ReLU networkscited by 28
  23. 2019Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuningcited by 24
  24. 2020Nonparametric Score Estimatorscited by 23
  25. 2021Meta-Learning Reliable Priors in the Function Spacecited by 23
  26. 2023Efficient Exploration in Continuous-time Model-based Reinforcement Learningcited by 22
  27. 2024Transductive Active Learning: Theory and Applicationscited by 22
  28. 2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
  29. 2023Hallucinated Adversarial Control for Conservative Offline Policy Evaluationcited by 13
  30. 2023Tuning Legged Locomotion Controllers via Safe Bayesian Optimizationcited by 9
  31. 2022Gradient-Based Trajectory Optimization With Learned Dynamicscited by 7
  32. 2023Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learningcited by 6
  33. 2017Fast Model Identification via Physics Engines for Data-Efficient Policy Searchcited by 5
  34. 2022Real-to-Sim: Predicting Residual Errors of Robotic Systems with Sparse Data using a Learning-based Unscented Kalman Filtercited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models
  2. 2024Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation
  3. 2024Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL
  4. 2026XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning
  5. 2025AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models
  6. 2016Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
  7. 2025SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training
  8. 2025Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling