While many multi-robot coordination problems can be solved optimally by exact algorithms, solutions are often not scalable in the number of robots. Multi-Agent Reinforcement Learning (MARL) is gaining increasing attention in the robotics community as a promising solution to tackle such problems. Nevertheless, we still lack the tools that allow us to quickly and efficiently find solutions to large-scale collective learning tasks. In this work, we introduce the Vectorized Multi-Agent Simulator (VMAS). VMAS is an open-source framework designed for efficient MARL benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of twelve challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface. We demonstrate how vectorization enables parallel simulation on accelerated hardware without added complexity. When comparing VMAS to OpenAI MPE, we show how MPE’s execution time increases linearly in the number of simulations while VMAS is able to execute 30,000 parallel simulations in under 10 s, proving more than 100 × \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times $$\end{document} faster. Using VMAS’s RLlib interface, we benchmark our multi-robot scenarios using various Proximal Policy Optimization (PPO)-based MARL algorithms. VMAS’s scenarios prove challenging in orthogonal ways for state-of-the-art MARL algorithms. The VMAS framework is available at: https://github.com/proroklab/VectorizedMultiAgentSimulator. A video of VMAS scenarios and experiments is available https://youtu.be/aaDRYfiesAY


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    VMAS: A Vectorized Multi-agent Simulator for Collective Robot Learning


    Weitere Titelangaben:

    Springer Proceedings in Advanced Robotics


    Beteiligte:
    Bourgeois, Julien (Herausgeber:in) / Paik, Jamie (Herausgeber:in) / Piranda, Benoît (Herausgeber:in) / Werfel, Justin (Herausgeber:in) / Hauert, Sabine (Herausgeber:in) / Pierson, Alyssa (Herausgeber:in) / Hamann, Heiko (Herausgeber:in) / Lam, Tin Lun (Herausgeber:in) / Matsuno, Fumitoshi (Herausgeber:in) / Mehr, Negar (Herausgeber:in)

    Kongress:

    International Symposium on Distributed Autonomous Robotic Systems ; 2022 ; Montbéliard, France November 28, 2022 - November 30, 2022



    Erscheinungsdatum :

    2024-02-01


    Format / Umfang :

    15 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    AGENT TRAJECTORY PREDICTION USING VECTORIZED INPUTS

    GAO JIYANG / SHEN YI / ZHAO HANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    AGENT TRAJECTORY PREDICTION USING VECTORIZED INPUTS

    GAO JIYANG / SHEN YI / ZHAO HANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    AGENT TRAJECTORY PREDICTION USING VECTORIZED INPUTS

    GAO JIYANG / SHEN YI / ZHAO HANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Intelligent agent trajectory prediction using vectorized input

    GAO JIYANG / SHEN YI / ZHAO HONG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Perfecting Vectorized Mechanical Drawings

    Chen, Y. / Langrana, N. A. / Das, A. K. | British Library Online Contents | 1996