Reinforcement learning (RL) is a form of machine learning (ML) where an agent is directed to a goal by learning from interactions within an environment. RL has been used to solve previously intractable problems such as Backgammon, Go, and Starcraft and offers a promising class of solutions to complex problems in various domains, including ones involving air and space. One of the major hindrances of using RL, more specifically deep RL (DRL), as a method is the variability with which an agent trains, which results from algorithm hyperparameters (e.g., batch size, training epochs, learning rate, etc.), deep neural network architectures (e.g., number of inputs, outputs, hidden layers and neurons in each layer, activation functions, connectivity, etc.), goal conditions, and reward functions. A slight modification to any of these factors can have a major impact on the training of the agent and the effectiveness of the learned policy. As such, hyperparameter and architecture searches are common practice in other domains involving neural networks. This work focuses on a systematic approach to DRL hyperparameter and architecture optimization for aerospace control systems using direct search, zeroth-order optimization, Bayesian optimization, and asynchronous hyperband-based training methods that are demonstrated in two different safety-critical aerospace environments and tasks, shedding light on general rules of thumb for RL applied to aerospace control systems.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement Learning Heuristics for Aerospace Control Systems


    Beteiligte:


    Erscheinungsdatum :

    2022-03-05


    Format / Umfang :

    7250831 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Safe Reinforcement Learning Benchmark Environments for Aerospace Control Systems

    Ravaioli, Umberto J. / Cunningham, James / McCarroll, John et al. | IEEE | 2022


    Learning 2-Opt Heuristics for Routing Problems via Deep Reinforcement Learning

    de O. da Costa, Paulo R. / Rhuggenaath, Jason / Zhang, Yingqian et al. | BASE | 2021

    Freier Zugriff

    Using Cases as Heuristics in Reinforcement Learning: A Transfer Learning Application

    Celiberto, Luiz A. / Matsuura, Jackson P. / López de Mántaras, Ramón et al. | BASE | 2011

    Freier Zugriff

    Verification of Adversarially Robust Reinforcement Learning Mechanisms in Aerospace Systems

    Seo, Taehwan / Sahoo, Prachi P. / Vamvoudakis, Kyriakos G. | AIAA | 2023


    Transferring knowledge as heuristics in reinforcement learning: A case-based approach

    Bianchi, Reinaldo / Celiberto, Luiz Antonio / Santos, Paulo Eduardo et al. | BASE | 2015

    Freier Zugriff