The objective of this research project was to improve Multi-Agent Reinforcement Learning performance in the StarCraft II environment with respect to faster training times, greater stability, and higher win ratios by 1) creating an adaptive action selector we call Adaptive Average Exploration, 2) using experiences previously learned by a neural network via Transfer Learning, and 3) updating the network simultaneously with its random action selector epsilon. We describe how agents interact with the StarCraft II environment and the QMIX algorithm used to test our approaches. We compare our AAE action selection approach with the default epsilon greedy method used by QMIX. These approaches are used to train Transfer Learning (TL) agents under a variety of test cases. We evaluate our TL agents using a predefined set of metrics. Finally, we demonstrate the effects of updating the neural networks and epsilon together more frequently on network performance.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adaptive Average Exploration in Multi-Agent Reinforcement Learning


    Contributors:


    Publication date :

    2020-10-11


    Size :

    1242761 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MARLAS: Multi Agent Reinforcement Learning for Cooperated Adaptive Sampling

    Pan, Lishuo / Manjanna, Sandeep / Hsieh, M. Ani | Springer Verlag | 2024


    Coordinated Multi-Robot Exploration using Reinforcement Learning

    Mete, Atharva / Mouhoub, Malek / Farid, Ali Moltajaei | IEEE | 2023


    Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments

    Peake, Ashley / McCalmon, Joe / Zhang, Yixin et al. | IEEE | 2021


    Multi-agent reinforcement learning method for fair adaptive traffic signal control

    ZHANG CHENGWEI / FANG WANQING / ZHAO XINTIAN | European Patent Office | 2023

    Free access

    Adaptive traffic signal control method based on multi-agent reinforcement learning

    ZHANG CHENGWEI / JIN SHAN / ZHENG KANGJIE | European Patent Office | 2021

    Free access