Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation

• URL: http://arxiv.org/abs/2603.15759v1
• Date: Mon, 16 Mar 2026 18:00:23 GMT
• Title: Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
• Abstract summary: Simulation Distillation (SimDist) is a framework that distills structural priors from a simulator into a latent world model.<n>By transferring reward and value models directly from simulation, SimDist provides dense planning signals from raw perception.<n>SimDist substantially outperforms prior methods in data efficiency, stability, and final performance.
• Score: 46.80452332618188
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simulation-to-real transfer remains a central challenge in robotics, as mismatches between simulated and real-world dynamics often lead to failures. While reinforcement learning offers a principled mechanism for adaptation, existing sim-to-real finetuning methods struggle with exploration and long-horizon credit assignment in the low-data regimes typical of real-world robotics. We introduce Simulation Distillation (SimDist), a sim-to-real framework that distills structural priors from a simulator into a latent world model and enables rapid real-world adaptation via online planning and supervised dynamics finetuning. By transferring reward and value models directly from simulation, SimDist provides dense planning signals from raw perception without requiring value learning during deployment. As a result, real-world adaptation reduces to short-horizon system identification, avoiding long-horizon credit assignment and enabling fast, stable improvement. Across precise manipulation and quadruped locomotion tasks, SimDist substantially outperforms prior methods in data efficiency, stability, and final performance. Project website and code: https://sim-dist.github.io/

Related papers

• RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning [19.985714275376726]
  We introduce RLFTSim, a reinforcement-learning-based fine-tuning framework.<n>It enhances scenario realism by aligning simulator rollouts with real-world data distributions.<n>We also demonstrate the effectiveness of our approach for distilling traffic simulation controllability through goal conditioning.
  arXiv  Detail & Related papers  (2026-05-18T18:57:13Z)
• ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation [90.4702774169675]
  We propose a novel hybrid approach called Compositional Simulation, which combines classical simulation and neural simulation.<n>Our approach utilizes a closed-loop real-sim-real data augmentation pipeline, leveraging a small amount of real-world data.<n>We train a neural simulator to transform classical simulation videos into real-world representations, improving the accuracy of policy models trained in real-world environments.
  arXiv  Detail & Related papers  (2026-04-13T12:25:45Z)
• HALO:Closing Sim-to-Real Gap for Heavy-loaded Humanoid Agile Motion Skills via Differentiable Simulation [22.6954724792851]
  We propose a two-stage gradient-based system identification framework built on the differentiable simulator MuJoCo XLA.<n>The first stage calibrates the nominal robot model using real-world data to reduce intrinsic sim-to-real discrepancies.<n>The second stage further identifies the mass distribution of the unknown payload.
  arXiv  Detail & Related papers  (2026-03-16T10:38:05Z)
• 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)
• Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning [20.72669976554826]
  Learned Graph Network Simulators (GNSs) offer a promising alternative to traditional mesh-based physics simulators.<n>Their speed and inherent differentiability make them well suited for applications that require fast and accurate simulations, such as robotic manipulation or manufacturing optimization.<n>We utilize movement primitives to directly predict fast, stable and accurate simulations from a single model call.
  arXiv  Detail & Related papers  (2025-11-07T13:34:02Z)
• Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning [13.771418136861831]
  Physics simulators can generate vast data sets with broad coverage over states, actions, and environments.<n>Fine-tuning these policies with small real-world data sets is an appealing pathway for scaling robot learning.<n>This paper introduces the Simulation-Guided Fine-tuning (SGFT) framework, which demonstrates how to extract structural priors from physics simulators.
  arXiv  Detail & Related papers  (2025-02-04T20:40:44Z)
• Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications [23.94013806312391]
  We propose a novel approach that dynamically adjusts simulation environment parameters online using in-context learning.<n>We validate our approach across two tasks: object scooping and table air hockey.<n>Our approach delivers efficient and smooth system identification, advancing the deployment of robots in dynamic real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-27T07:13:38Z)
• Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning [22.077058792635313]
  Coverage path planning is the problem of finding a path that covers the entire free space of a confined area.<n>We investigate the suitability of continuous-space reinforcement learning for this challenging problem.<n>We show that our approach surpasses the performance of both previous RL-based approaches and highly specialized methods.
  arXiv  Detail & Related papers  (2024-06-07T13:24:19Z)
• 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)
• TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors [74.67698916175614]
  We propose TrafficSim, a multi-agent behavior model for realistic traffic simulation. In particular, we leverage an implicit latent variable model to parameterize a joint actor policy. We show TrafficSim generates significantly more realistic and diverse traffic scenarios as compared to a diverse set of baselines.
  arXiv  Detail & Related papers  (2021-01-17T00:29:30Z)
• Reactive Long Horizon Task Execution via Visual Skill and Precondition Models [59.76233967614774]
  We describe an approach for sim-to-real training that can accomplish unseen robotic tasks using models learned in simulation to ground components of a simple task planner. We show an increase in success rate from 91.6% to 98% in simulation and from 10% to 80% success rate in the real-world as compared with naive baselines.
  arXiv  Detail & Related papers  (2020-11-17T15:24:01Z)
• Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [62.22058066456076]
  Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks. RL does not work directly in the real-world, which is known as the sim-to-real transfer problem. We propose a method that learns on an observation space constructed by point clouds and environment randomization.
  arXiv  Detail & Related papers  (2020-07-27T17:46:59Z)

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.