Aerospace battle scenarios represent a challenging modeling effort, often requiring large, continuous, and simultaneous state and/ or action spaces with imperfect information. We model a battle as a Multi-Stage Markov Stochastic Game (MSMSG) and facilitate agent decision making using a Double Deep Q-Network (DDQN) paradigm with Minimax Q-Learning. We demonstrate our model performance in contrast with a DDQN agent trained using a traditional Q-learning algorithm in a 1D dynamic battle environment. Preliminary findings suggest that the DDQN + Minimax-Q agent is more robust to parameter tuning and can learn true optimal mixed strategies compared to its traditional Q-learning counterpart.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Agent Decision Processes Using Double Deep Q-Networks + Minimax Q- Learning


    Beteiligte:
    Fitch, Natalie (Autor:in) / Clancy, Daniel (Autor:in)


    Erscheinungsdatum :

    06.03.2021


    Format / Umfang :

    7037750 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processes

    Menda, Kunal / Chen, Yi-Chun / Grana, Justin et al. | IEEE | 2019


    Minimax Reinforcement Learning

    Chakravorty, Suman / Hyland, David | AIAA | 2003