Reinforcement learning tree-based planning methods have been gaining popularity in the last few years due to their success in single-agent domains, where a perfect simulator model is available: for example, Go and chess strategic board games. This paper pretends to extend tree search algorithms to the multiagent setting in a decentralized structure, dealing with scalability issues and exponential growth of computational resources. The n - step dynamic tree search combines forward planning and direct temporal-difference updates, outperforming markedly conventional tabular algorithms such as Q learning and state-action-reward-state-action (SARSA). Future state transitions and rewards are predicted with a model built and learned from real interactions between agents and the environment. This paper analyzes the developed algorithm in the hunter–pursuit cooperative game against stochastic and intelligent evaders. The n - step dynamic tree search aims to adapt single-agent tree search learning methods to the multiagent boundaries and is demonstrated to be a remarkable advance as compared to conventional temporal-difference techniques.


    Access

    Download


    Export, share and cite



    Title :

    Swarm Intelligence in Cooperative Environments: n -Step Dynamic Tree Search Algorithm Overview


    Contributors:

    Published in:

    Publication date :

    2023-07-01




    Type of media :

    Conference paper , Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Swarm Intelligence in Cooperative Environments: Introducing the N-Step Dynamic Tree Search Algorithm

    Longa, Marc Espinós / Inalhan, Gokhan / Tsourdos, Antonios | TIBKAT | 2022


    Swarm Intelligence in Cooperative Environments: Introducing the N-Step Dynamic Tree Search Algorithm

    Espinós Longa, Marc / Inalhan, Gokhan / Tsourdos, Antonios | AIAA | 2022


    Overview of cooperative UAV swarm localization

    Shangguan, Runzong / Lin, Lin / Zhou, Yanbo | SPIE | 2025


    A hybrid cooperative cuckoo search algorithm with particle swarm optimisation

    Wang, Lijin / Zhong, Yiwen / Yin, Yilong | British Library Online Contents | 2015


    A hybrid cooperative cuckoo search algorithm with particle swarm optimisation

    Wang, Lijin / Zhong, Yiwen / Yin, Yilong | British Library Online Contents | 2015