Simulation Priors for Data-Efficient Deep Learning

• URL: http://arxiv.org/abs/2509.05732v1
• Date: Sat, 06 Sep 2025 14:36:41 GMT
• Title: Simulation Priors for Data-Efficient Deep Learning
• Authors: Lenart Treven, Bhavya Sukhija, Jonas Rothfuss, Stelian Coros, Florian Dörfler, Andreas Krause,
• Abstract summary: SimPEL is a method that efficiently combines first-principles models with data-driven learning.<n>We evaluate SimPEL on diverse systems, including biological, agricultural, and robotic domains.<n>For decision-making, we demonstrate that SimPEL bridges the sim-to-real gap in model-based reinforcement learning.
• Score: 56.525770511247934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping [66.22412592525369]
  We introduce a real-to-sim-to-real engine that leverages the Gaussian Splat representations to build a differentiable engine.<n>We show that our engine achieves accurate and robust performance in mass identification across various object geometries and mass values.<n>Those optimized mass values facilitate force-aware policy learning, achieving superior and high performance in object grasping.
  arXiv  Detail & Related papers  (2026-03-01T15:32:04Z)
• SimScale: Learning to Drive via Real-World Simulation at Scale [45.08991279559151]
  We introduce a novel and scalable simulation framework capable of synthesizing massive unseen states upon existing driving logs.<n>Our pipeline utilizes advanced neural rendering with a reactive environment to generate high-fidelity multi-view observations.<n>We develop a pseudo-expert trajectory generation mechanism for these newly simulated states to provide action supervision.
  arXiv  Detail & Related papers  (2025-11-28T17:17:38Z)
• Physics-Learning AI Datamodel (PLAID) datasets: a collection of physics simulations for machine learning [0.15469999759898032]
  PLAID is a framework for representing and sharing datasets of physics simulations.<n> PLAID defines a unified standard for describing simulation data.<n>We release six datasets under the PLAID standard, covering structural mechanics and computational fluid dynamics.
  arXiv  Detail & Related papers  (2025-05-05T18:59:17Z)
• Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models [9.318262213262866]
  We introduce a novel framework for learning semi-structured dynamics models for contact-rich systems. We make accurate long-horizon predictions with substantially less data than prior methods. We validate our approach on a real-world Unitree Go1 quadruped robot.
  arXiv  Detail & Related papers  (2024-10-11T18:11:21Z)
• Bridging the Sim-to-Real Gap with Bayesian Inference [53.61496586090384]
  We present SIM-FSVGD for learning robot dynamics from data. We use low-fidelity physical priors to regularize the training of neural network models. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system.
  arXiv  Detail & Related papers  (2024-03-25T11:29:32Z)
• Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning [61.3506230781327]
  In robotics, one approach to generate training data builds on simulations based on dynamics models derived from first principles. Here, we leverage the imbalance in complexity of the dynamics to learn more sample-efficiently. We validate our method on several challenging simulated tasks and demonstrate that it improves learning both alone and when combined with an existing hindsight algorithm.
  arXiv  Detail & Related papers  (2023-03-03T21:55:04Z)
• Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation [49.631034790080406]
  We present a task for navigating a marble to the center of a circular maze. We present a model that learns to move a marble in the complex environment within minutes of interacting with the real system.
  arXiv  Detail & Related papers  (2020-11-14T02:03:08Z)
• Information Theoretic Model Predictive Q-Learning [64.74041985237105]
  We present a novel theoretical connection between information theoretic MPC and entropy regularized RL. We develop a Q-learning algorithm that can leverage biased models.
  arXiv  Detail & Related papers  (2019-12-31T00:29:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.