Active research in autonomous unmanned aerial vehicles (UAVs) seeks to combine the agility of Proportional-Integral-Derivative (PID) systems for low-level control with the adaptability of Deep Reinforcement Learning (DRL) to navigate through challenging, non-stationary environments. In the real world, there is often a need to quickly adapt trained DRL agents to more difficult tasks with conflicting rewards. For efficient retraining, the ability to leverage previously learned skills becomes critical. Unfortunately, using traditional DRL algorithms like soft actor critic (SAC) for retraining a policy can lead to catastrophic forgetting of the policy’s known skills. In this work, inspired by neuroscience research, we propose a novel approach using SAC with inhibitory networks to allow separate and adaptive state value evaluations, as well as distinct automatic entropy tuning. We validate our method through experiments using a quadcopter in a realistic simulation environment and demonstrate the advantage of retraining. Moreover, we present the superiority of our approach compared to baseline methods with respect to both sample efficiency and cumulative success.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Soft Actor-Critic with Inhibitory Networks for Retraining UAV Controllers Faster


    Beteiligte:
    Choi, Minkyu (Autor:in) / Filter, Max (Autor:in) / Alcedo, Kevin (Autor:in) / Walker, Thayne T. (Autor:in) / Rosenbluth, David (Autor:in) / Ide, Jaime S. (Autor:in)


    Erscheinungsdatum :

    2022-06-21


    Format / Umfang :

    2938638 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multiagent Soft Actor–Critic for Traffic Light Timing

    Wu, Lan / Wu, Yuanming / Qiao, Cong et al. | ASCE | 2023


    Stepwise Soft Actor–Critic for UAV Autonomous Flight Control

    Ha Jun Hwang / Jaeyeon Jang / Jongkwan Choi et al. | DOAJ | 2023

    Freier Zugriff

    Meta Soft Actor-Critic Based Robust Sequential Power Control in Vehicular Networks

    Liu, Zhihua / Guo, Chongtao / Guo, Cheng et al. | IEEE | 2023


    Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic

    Ren, Yangang / Duan, Jingliang / Li, Shengbo Eben et al. | IEEE | 2020