In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization distributions can be difficult. In this paper, we introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. Unlike prior work, DROPO only requires a limited, precollected offline dataset of trajectories, and explicitly models parameter uncertainty to match real data using a likelihood-based approach. We demonstrate that DROPO is capable of recovering dynamic parameter distributions in simulation and finding a distribution capable of compensating for an unmodeled phenomenon. We also evaluate the method in two zero-shot sim-to-real transfer scenarios, showing successful domain transfer and improved performance over prior methods. & COPY; 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).


    Access

    Download


    Export, share and cite



    Title :

    DROPO: Sim-to-real transfer with offline domain randomization



    Publication date :

    2023-01-01



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Online vs. Offline Adaptive Domain Randomization Benchmark

    Tiboni, Gabriele / Arndt, Karol / Averta, Giuseppe et al. | Springer Verlag | 2023



    Real-time and Offline Filters for Eye Tracking

    Olsson, Pontus | BASE | 2007

    Free access

    Offline transfer trolley for cylinder sleeve machining

    GONG TIANPING / ZHOU ZHENGMIN / ZHOU GUORONG | European Patent Office | 2022

    Free access

    Monocular Camera and Single-Beam Sonar-Based Underwater Collision-Free Navigation with Domain Randomization

    Yang, Pengzhi / Liu, Haowen / Roznere, Monika et al. | Springer Verlag | 2023