When robots share the same workspace with other intelligent agents (e.g., other robots or humans), they must be able to reason about the behaviors of their neighboring agents while accomplishing the designated tasks. In practice, frequently, agents do not exhibit absolutely rational behavior due to their limited computational resources. Thus, predicting the optimal agent behaviors is undesirable (because it demands prohibitive computational resources) and undesirable (because the prediction may be wrong). Motivated by this observation, we remove the assumption of perfectly rational agents and propose incorporating the concept of bounded rationality from an information-theoretic view into the game-theoretic framework. This allows the robots to reason other agents’ sub-optimal behaviors and act accordingly under their computational constraints. Specifically, bounded rationality directly models the agent’s information processing ability, which is represented as the KL-divergence between nominal and optimized stochastic policies, and the solution to the bounded-optimal policy can be obtained by an efficient importance sampling approach. Using both simulated and real-world experiments in multi-robot navigation tasks, we demonstrate that the resulting framework allows the robots to reason about different levels of rational behaviors of other agents and compute a reasonable strategy under its computational constraint. ( 1 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{1}$$\end{document}A preliminary version of this work appeared as a poster in 2021 NeurIPS Workshop on Learning and Decision-Making with Strategic Feedback.

    The video of the real-world experiments can be found at https://youtu.be/hzCitSSuWiI.

    We gratefully acknowledge the support of NSF with grant No. 2006886 and 2047169.)


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Decision-Making Among Bounded Rational Agents


    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 :

    13 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Procedurally Rational Decision-Making and Control

    Stirling, W. C. / Goodrich, M. A. / Frost, R. L. | British Library Online Contents | 1996


    Bounded awareness: Implications for ethical decision making

    Bazerman, Max H | Online Contents | 2016


    Bounded rational choice behaviour: applications in transport

    Jensen, Anders Fjendbo | Taylor & Francis Verlag | 2016


    Bounded rational choice behaviour : applications in transport

    Rasouli, Soora ;Timmermans, Harry J. P. | TIBKAT | 2015