Provable Sim-to-Real Transfer via Offline Domain Randomization

• URL: http://arxiv.org/abs/2506.10133v1
• Date: Wed, 11 Jun 2025 19:22:33 GMT
• Title: Provable Sim-to-Real Transfer via Offline Domain Randomization
• Abstract summary: A dominant strategy for reducing the sim-to-real gap is domain randomization (DR)<n>Standard DR ignores offline data already available from the real system.<n>We study offline domain randomization (ODR), which first fits a distribution over simulator parameters to an offline dataset.
• Score: 7.102939706790656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement-learning agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulators produced by sampling dynamics parameters, but standard DR ignores offline data already available from the real system. We study offline domain randomization (ODR), which first fits a distribution over simulator parameters to an offline dataset. While a growing body of empirical work reports substantial gains with algorithms such as DROPO, the theoretical foundations of ODR remain largely unexplored. In this work, we (i) formalize ODR as a maximum-likelihood estimation over a parametric simulator family, (ii) prove consistency of this estimator under mild regularity and identifiability conditions, showing it converges to the true dynamics as the dataset grows, (iii) derive gap bounds demonstrating ODRs sim-to-real error is up to an O(M) factor tighter than uniform DR in the finite-simulator case (and analogous gains in the continuous setting), and (iv) introduce E-DROPO, a new version of DROPO which adds an entropy bonus to prevent variance collapse, yielding broader randomization and more robust zero-shot transfer in practice.

Related papers

• Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection [58.25418970608328]
  We study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains.<n>Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution.<n>We propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem.
  arXiv  Detail & Related papers  (2026-07-08T09:27:15Z)
• Joint Model and Data Sparsification via the Marginal Likelihood [53.29070892356214]
  We propose jointly learning individual feature and sample relevancies, enabling simultaneous model and data sparsification.<n>This symmetric pruning of model and data offers a natural extension that preserves conjugacy.<n> Empirical results across diverse regression tasks affirm that a joint ARD approach consistently yields both sparse and robust prediction models.
  arXiv  Detail & Related papers  (2026-05-28T13:26:53Z)
• Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces [81.41397370235102]
  We introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data.<n>We show that current models struggle to accurately simulate complex behaviors, with performance plateauing even as context windows expand.<n>This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.
  arXiv  Detail & Related papers  (2026-04-09T15:26:21Z)
• Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving [54.46325690390831]
  We propose Model-based Policy Adaptation (MPA), a general framework that enhances the robustness and safety of pretrained E2E driving agents during deployment.<n>MPA first generates diverse counterfactual trajectories using a geometry-consistent simulation engine.<n>MPA trains a diffusion-based policy adapter to refine the base policy's predictions and a multi-step Q value model to evaluate long-term outcomes.
  arXiv  Detail & Related papers  (2025-11-26T17:01:41Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Offline Robotic World Model: Learning Robotic Policies without a Physics Simulator [50.191655141020505]
  Reinforcement Learning (RL) has demonstrated impressive capabilities in robotic control but remains challenging due to high sample complexity, safety concerns, and the sim-to-real gap.<n>We introduce Offline Robotic World Model (RWM-O), a model-based approach that explicitly estimates uncertainty to improve policy learning without reliance on a physics simulator.
  arXiv  Detail & Related papers  (2025-04-23T12:58:15Z)
• Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model [66.91323540178739]
  Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior. We revisit SR from a novel information-theoretic perspective and find that sequential modeling methods fail to adequately capture randomness and unpredictability of user behavior. Inspired by fuzzy information processing theory, this paper introduces the fuzzy sets of interaction sequences to overcome the limitations and better capture the evolution of users' real interests.
  arXiv  Detail & Related papers  (2024-10-31T14:52:01Z)
• LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots [20.715834172041763]
  We propose LoopSR, a lifelong policy adaptation framework that continuously refines RL policies in the post-deployment stage.<n>LoopSR employs a transformer-based encoder to map real-world trajectories into a latent space.<n>Autoencoder architecture and contrastive learning methods are adopted to enhance feature extraction of real-world dynamics.
  arXiv  Detail & Related papers  (2024-09-26T16:02:25Z)
• Distributionally Robust Optimization as a Scalable Framework to Characterize Extreme Value Distributions [22.765095010254118]
  The goal of this paper is to develop distributionally robust optimization (DRO) estimators, specifically for multidimensional Extreme Value Theory (EVT) statistics. In order to mitigate over-conservative estimates while enhancing out-of-sample performance, we study DRO estimators informed by semi-parametric max-stable constraints in the space of point processes. Both approaches are validated using synthetically generated data, recovering prescribed characteristics, and verifying the efficacy of the proposed techniques.
  arXiv  Detail & Related papers  (2024-07-31T19:45:27Z)
• Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
  Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
  arXiv  Detail & Related papers  (2024-04-11T09:23:36Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• Domain Randomization via Entropy Maximization [32.76511125425768]
  We propose a novel approach to address sim-to-real transfer, which automatically shapes dynamics distributions during training in simulation without requiring real-world data. We introduce DOmain RAndomization via Entropy MaximizatiON (DORAEMON), a constrained optimization problem that directly maximizes the entropy of the training distribution. We empirically validate the consistent benefits of DORAEMON in obtaining highly adaptive and generalizable policies.
  arXiv  Detail & Related papers  (2023-11-03T12:54:05Z)
• Robust Visual Sim-to-Real Transfer for Robotic Manipulation [79.66851068682779]
  Learning visuomotor policies in simulation is much safer and cheaper than in the real world. However, due to discrepancies between the simulated and real data, simulator-trained policies often fail when transferred to real robots. One common approach to bridge the visual sim-to-real domain gap is domain randomization (DR)
  arXiv  Detail & Related papers  (2023-07-28T05:47:24Z)
• Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation [52.73824786627612]
  This paper establishes new convergence results for textitgeodesic strongly monotone games.<n>Our key result shows that RGD attains last-iterate linear convergence in a textitgeometry-agnostic fashion.<n>Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• DROPO: Sim-to-Real Transfer with Offline Domain Randomization [12.778412161239466]
  We introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. We demonstrate that DROPO is capable of recovering dynamic parameter distributions in simulation and finding a distribution capable of compensating for an unmodelled phenomenon.
  arXiv  Detail & Related papers  (2022-01-20T20:03:35Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)
• DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning [4.040937987024427]
  Domain Randomization(DR) is a methodology that can bridge this gap with little or no real-world data. An adversarial model is put forward to robustify DeepRL-based autonomous vehicles trained in simulation.
  arXiv  Detail & Related papers  (2021-07-25T09:15:46Z)

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.