Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications. In this work, we approach an alternative Interactive Machine Learning (IML) strategy for training DNN policies based on human corrective feedback, with a method called Deep COACH (D-COACH). This approach not only takes advantage of the knowledge and insights of human teachers as well as the power of DNNs, but also has no need of a reward function (which sometimes implies the need of external perception for computing rewards). We combine Deep Learning with the COrrective Advice Communicated by Humans (COACH) framework, in which non-expert humans shape policies by correcting the agent’s actions during execution. The D-COACH framework has the potential to solve complex problems without much data or time required. Experimental results validated the efficiency of the framework in three different problems (two simulated, one with a real robot), with state spaces of low and high dimensions, showing the capacity to successfully learn policies for continuous action spaces like in the Car Racing and Cart-Pole problems faster than with DRL.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Interactive Learning with Corrective Feedback for Policies Based on Deep Neural Networks


    Additional title:

    Springer Proceedings in Advanced Robotics



    Conference:

    International Symposium on Experimental Robotics ; 2018 ; Buenos Aires, Argentina November 05, 2018 - November 08, 2018



    Publication date :

    2020-01-23


    Size :

    11 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Interactive Learning with Corrective Feedback for Policies Based on Deep Neural Networks

    Pérez-Dattari, Rodrigo / Celemin, Carlos / Ruiz-del-Solar, Javier et al. | TIBKAT | 2020


    Deep Reinforcement Learning with Corrective Feedback for Autonomous UAV Landing on a Mobile Platform

    Lizhen Wu / Chang Wang / Pengpeng Zhang et al. | DOAJ | 2022

    Free access

    Learning Deep Neural Policies with Stability Guarantees

    Abdul Khader, Shahbaz / Yin, Hang / Falco, Pietro et al. | BASE

    Free access

    Error-corrective optical neural networks modelled by persistent spectral hole-burning

    Ollikainen, O. / Rebane, A. / Rebane, K. K. | British Library Online Contents | 1993


    Interactive Learning in Artificial Neural Networks through Visualization

    Mohamed, A. S. | British Library Online Contents | 1998