In this paper, we address the inverse problem in the case of linear–quadratic zero-sum differential games. The problem is to evaluate an unknown cost function given the observed trajectories that are known to be generated by a stationary linear feedback Nash equilibrium pair. Using the observed data, we construct a game that is equivalent to the game that leads to the observed trajectories in the sense that the equilibrium feedback law of any of the two player is the same for that player in the original and constructed games. Towards this end, we introduce a model-based algorithm that uses the given trajectories to accomplish this task. The algorithm combines both inverse optimal control and reinforcement learning methods making extensive use of gradient descent optimization for the latter. The analysis of the algorithm focuses on the proof of its convergence and stability. Simulation results validate the effectiveness of the proposed algorithm.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Inverse reinforcement learning for identification of linear–quadratic zero-sum differential games


    Beteiligte:
    Martirosyan, E. (Autor:in) / Cao, M. (Autor:in)

    Erscheinungsdatum :

    2023-02-01


    Anmerkungen:

    Martirosyan , E & Cao , M 2023 , ' Inverse reinforcement learning for identification of linear–quadratic zero-sum differential games ' , Systems & Control Letters , vol. 172 , 105438 . https://doi.org/10.1016/j.sysconle.2022.105438



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629



    Inverse Reinforcement Learning for Identification in Linear-Quadratic Dynamic Games

    Köpf, Florian / Inga, Jairo / Rothfuß, Simon et al. | BASE | 2017

    Freier Zugriff

    Linear Quadratic Differential Games Guidance Law for Autonomous Aerial Refueling

    Tal, Ezra Amram / Shima, Tal | British Library Conference Proceedings | 2015



    Trajectory Shaping and Terminal Guidance Using Linear Quadratic Differential Games

    Levinson, Sergei / Weiss, Haim / Ben-Asher, Joseph Z. | AIAA | 2002