Embodied evolution is a methodology for evolutionary robotics that mimics the distributed, asynchronous, and autonomous properties of biological evolution. The evaluation, selection, and reproduction are carried out by cooperation and competition of the robots, without any need for human intervention. An embodied evolution framework is therefore well suited to study the adaptive learning mechanisms for artificial agents that share the same fundamental constraints as biological agents: self-preservation and self-reproduction. The main goal of the research in this thesis has been to develop a framework for performing embodied evolution with a limited number of robots, by utilizing time-sharing of subpopulations of virtual agents inside each robot. The framework integrates reproduction as a directed autonomous behavior, and allows for learning of basic behaviors for survival by reinforcement learning. The purpose of the evolution is to evolve the learning ability of the agents, by optimizing meta-properties in reinforcement learning, such as the selection of basic behaviors, meta-parameters that modulate the efficiency of the learning, and additional and richer reward signals that guides the learning in the form of shaping rewards. The realization of the embodied evolution framework has been a cumulative research process in three steps: 1) investigation of the learning of a cooperative mating behavior for directed autonomous reproduction; 2) development of an embodied evolution framework, in which the selection of pre-learned basic behaviors and the optimization of battery recharging are evolved; and 3) development of an embodied evolution framework that includes meta-learning of basic reinforcement learning behaviors for survival, and in which the individuals are evaluated by an implicit and biologically inspired fitness function that promotes reproductive ability. The proposed embodied evolution methods have been validated in a simulation environment of the Cyber Rodent robot, a robotic platform developed for ...


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Embodied Evolution of Learning Ability


    Beteiligte:

    Erscheinungsdatum :

    2007-01-01


    Medientyp :

    Hochschulschrift


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Embodied evolution in collective robotics:A review

    Bredeche, Nicolas / Haasdijk, Evert / Prieto, Abraham | BASE | 2018

    Freier Zugriff

    Innately adaptive robotics through embodied evolution

    Mahdavi, S. H. / Bentley, P. J. | British Library Online Contents | 2006


    On the evolution of behaviors through embodied imitation

    Erbaş, Mehmet D. / Bull, Larry / Winfield, Alan F. T. | BASE | 2015

    Freier Zugriff

    Hierarchies for embodied action perception

    Ognibene D / Wu Yan / Lee Kyuhwa et al. | BASE | 2013

    Freier Zugriff

    Embodied Flight with a Drone

    Cherpillod, Alexandre / Floreano, Dario / Mintchev, Stefano | IEEE | 2019