Automated Reinforcement Learning (AutoRL) is a relatively new area of research that is gaining increasing attention. The objective of AutoRL consists in easing the employment of Reinforcement Learning (RL) techniques for the broader public by alleviating some of its main challenges, including data collection, algorithm selection, and hyper-parameter tuning. In this work, we propose a general and flexible framework, namely ARLO: Automated Reinforcement Learning Optimizer, to construct automated pipelines for AutoRL. Based on this, we propose a pipeline for offline and one for online RL, discussing the components, interaction, and highlighting the difference between the two settings. Furthermore, we provide a Python implementation of such pipelines, released as an open-source library. Our implementation is tested on an illustrative LQG domain and on classic MuJoCo environments, showing the ability to reach competitive performances requiring limited human intervention. We also showcase the full pipeline on a realistic dam environment, automatically performing the feature selection and the model generation tasks.


    Access

    Download


    Export, share and cite



    Title :

    ARLO: A framework for Automated Reinforcement Learning



    Publication date :

    2023-01-01



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629





    Distributional Reinforcement Learning For Automated Driving Vehicle

    Naveen, A M / Ravish, Roopa / Ranga Swamy, Shanta | IEEE | 2022


    Automated Adaptive Traffic Corridor Control Using Reinforcement Learning

    Jacob, Celine / Abdulhai, Baher | Transportation Research Record | 2006


    Reinforced logistics: Automated tour planning with reinforcement learning

    Kemmerling, Marco / Haßler, Marc / Solvay, Alexia Fenollar et al. | DataCite | 2020