Reinforcement Learning has been proven to be successfully applied in robotic manipulation tasks, but it has been confronted with problems about interacting with the dynamic environment and generating high-level policies. Existing reward functions include sparse and shaped reward, and other way to view the reward functions as black boxes and then discover the best strategies by interacting with the environment. In this paper, a reward machine with demonstration definition for robot assembly is presented, which is a finite state machine that supports generating the specified reward function from the demonstration data and displays the reward function structure. By dividing the task demonstration data, extracting the key points of the task and defining the state of the robot, a reward function based on state migration is generated. The robot chooses the best reward according to the current state, which is conducive to using the reward structure to improve the sample efficiency and the quality of the result strategy. In this paper, we focus on the robot assembly reinforcement learning task. The structure of the proposed method is used to carry out experiments in the robot simulator. We compare the design methods with different reward functions and it proves that the proposed method can effectively improve the training efficiency of robot reinforcement learning.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Demonstration Shaped Reward Machine for Robot Assembly Reinforcement Learning Tasks


    Weitere Titelangaben:

    Lect.Notes Computer


    Beteiligte:
    Yang, Huayong (Herausgeber:in) / Liu, Honghai (Herausgeber:in) / Zou, Jun (Herausgeber:in) / Yin, Zhouping (Herausgeber:in) / Liu, Lianqing (Herausgeber:in) / Yang, Geng (Herausgeber:in) / Ouyang, Xiaoping (Herausgeber:in) / Wang, Zhiyong (Herausgeber:in) / Xiao, Ruihong (Autor:in) / Zhan, Hong (Autor:in)

    Kongress:

    International Conference on Intelligent Robotics and Applications ; 2023 ; Hangzhou, China July 05, 2023 - July 07, 2023



    Erscheinungsdatum :

    16.10.2023


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Demonstration Shaped Reward Machine for Robot Assembly Reinforcement Learning Tasks

    Xiao, Ruihong / Zhan, Hong / Jiang, Yiming et al. | TIBKAT | 2023


    Reinforcement learning reward function in unmanned aerial vehicle control tasks

    Tovarnov, Mikhail S. / Bykov, Nikita V. | ArXiv | 2022

    Freier Zugriff


    Towards Learning by Demonstration for Industrial Assembly Tasks

    Hernandez Moreno, Victor / Carmichael, Marc G. / Deuse, Jochen | Springer Verlag | 2023

    Freier Zugriff