This paper details progress within the Multi-Agent Reinforcement Learning (MARL) research area with application to agent decision processing in complex battle-space scenarios, including air, surface, sub-surface, and space domains. We implement a Double Deep Q-Network (DDQN) with Minimax Q-Learning in order to model simultaneous, zero-sum, two team engagements involving multiple Blue agents & Red opponents. This is a game theoretic approach that models both ally and opponent policies while viewing a battle as a Multi-Stage Markov Stochastic Game (MSMSG). We contrast our agent with a DDQN + Traditional Q-Learning algorithm in a single stage 2v1 battle scenario with mixed optimal strategies. In order to help mitigate learning sensitivities and local optima convergence, we implement a Genetic Programming (GP) algorithm, which outperforms both the Minimax Q-Learning and Traditional Q-Learning DDQN agents trained using traditional stochastic gradient descent in a dynamic 1v1 battle. Lastly, we create a hybrid approach that combines stochastic gradient descent learning (Minimax Q-Learning) and gradient-free learning (GP) and apply our hybrid approach within the StarCraft II (SC2) 3m map, which simulates a 3v3 battle. We contrast this hybrid MARL approach with another state-of-the-art MARL method (QMIX) for the SC2 3m combat scenario.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Genetic Programming + Multi-Agent Reinforcement Learning: Hybrid Approaches for Decision Processes


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


    Erscheinungsdatum :

    05.03.2022


    Format / Umfang :

    1853678 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


    Intersection decision-making method based on multi-agent deep reinforcement learning

    DU YU / JIANG ANNI / ZHAO SHIXIN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Genetic-Algorithm-Aided Deep Reinforcement Learning for Multi-Agent Drone Delivery

    Farabi Ahmed Tarhan / Nazım Kemal Ure | DOAJ | 2024

    Freier Zugriff

    Decision-Making for Priority Vehicle Transit Based on Multi-agent Reinforcement Learning

    Yang, Yi / Huang, Zhongguo / Gu, Qing et al. | Springer Verlag | 2025