In this work, we propose a new method for obtaining heuristics based on Reinforcement Learning (RL). The synthesis algorithm is thus framed as an RL task with an unbounded action space and a modified version of DQN is used. With a simple and general set of features that abstracts both states and actions, we show that it is possible to learn heuristics on small versions of a problem that generalize to the larger instances, effectively doing zero-shot policy transfer. Our agents learn from scratch in a highly partially observable RL task and outperform the existing heuristic overall, in instances unseen during training. ; Agencia Nacional de Promoción de la Investigación, el Desarrollo Tecnológico y la Innovación ; Universidad de Buenos Aires ; Agencia Nacional de Investigación e Innovación


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach


    Beteiligte:

    Erscheinungsdatum :

    2023-07-08


    Anmerkungen:

    33rd International Conference on Automated Planning and Scheduling. Prague, Czech Republic. 2023



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Learning Urban Driving Policies using Deep Reinforcement Learning

    Agarwal, Tanmay / Arora, Hitesh / Schneider, Jeff | IEEE | 2021


    DEEP REINFORCEMENT LEARNING FOR OPTIMIZING CARPOOLING POLICIES

    JINDAL ISHAN / QIN ZHIWEI / CHEN XUEWEN et al. | Europäisches Patentamt | 2019

    Freier Zugriff

    DEEP REINFORCEMENT LEARNING FOR OPTIMIZING CARPOOLING POLICIES

    JINDAL ISHAN / QIN ZHIWEI / CHEN XUEWEN et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Safe Exploration in Model-Based Reinforcement Learning

    Cohen, Max / Belta, Calin | Springer Verlag | 2023


    Improve PID controller through reinforcement learning

    Qin, Yunxiao / Zhang, Weiguo / Shi, Jingping et al. | IEEE | 2018