In this work, we develop the transfer learning (TL) of reinforcement learning (RL) for the robotic skill of throwing a ball into a basket, from a computer simulated environment to a real-world implementation. Whereas learning of the same skill has been previously explored by using a Programming by Demonstration approach directly on the real-world robot, for our work, the model-based RL algorithm PILCO was employed as an alternative as it provides the robot with no previous knowledge or hints, i.e. the robot begins learning from a tabula rasa state, PILCO learns directly on the simulated environment, and as part of its procedure, PILCO models the dynamics of the inflatable, plastic ball used to perform the task. The robotic skill is represented as a Markov Decision Process, the robotic arm is a Kuka LWR4+, RL is enabled by PILCO, and TL is achieved through policy adjustments. Two learned policies were transferred, and although the results show that no exhaustive policy adjustments are required, large gaps remain between the simulated and the real environment in terms of the ball and robot dynamics. The contributions of this thesis include: a novel TL of RL framework for teaching the basketball skill to the Kuka robotic arm; the development of a pythonised version of PILCO; robust and extendable ROS packages for policy learning and adjustment in a simulated or real robot; a tracking-vision package with a Kinect camera; and an Orocos package for a position controller in the robotic arm.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Transfer of reinforcement learning for a robotic skill


    Beteiligte:

    Erscheinungsdatum :

    2018-01-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Framework for robot skill learning using reinforcement learning [5253-193]

    Wei, Y. / Zhao, M. / SPIE - The International Society for Optical Engineering | British Library Conference Proceedings | 2003


    Core Skill Decomposition of Complex Wargames with Reinforcement Learning

    Kömürcü, Kubilay K. / Ince, Batuhan / Ok, Tolga et al. | AIAA | 2022



    Core Skill Decomposition of Complex Wargames with Reinforcement Learning

    Komurcu, Kubilay K. / Ince, Batuhan / Ok, Tolga et al. | TIBKAT | 2022