Sökning: "reinforcement learning"

Visar resultat 11 - 15 av 175 avhandlingar innehållade orden reinforcement learning.

  1. 11. Learning-by-modeling : Novel Computational Approaches for Exploring the Dynamics of Learning and Self-governance in Social-ecological Systems

    Författare :Emilie Lindkvist; Maja Schlüter; Jon Norberg; Örjan Ekeberg; James Dyke; Stockholms universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Complex adaptive systems; Renewable resources; Adaptive management; Small-scale fisheries; Artificial intelligence; Reinforcement learning; Agent-based modeling; agent-baserade modeller; artificiell intelligens; social-ekologiska system; komplexa adaptiva system; förnyelsebara naturresurser; adaptiv förvaltning; Sustainability Science; vetenskap om hållbar utveckling;

    Sammanfattning : As a consequence of global environmental change, sustainable management and governance of natural resources face critical challenges, such as dealing with non-linear dynamics, increased resource variability, and uncertainty. This thesis seeks to address some of these challenges by using simulation models. LÄS MER

  3. 12. Sensorimotor Robot Policy Training using Reinforcement Learning

    Författare :Ali Ghadirzadeh; Mårten Björkman; Danica Kragic; Atsuto Maki; Ville Kyrki; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Reinforcement Learning; Artificial Intelligence; Robot Learning; Sensorimotor; Policy Training; Computer Science; Datalogi;

    Sammanfattning : Robots are becoming more ubiquitous in our society and taking over many tasks that were previously considered as human hallmarks. Many of these tasks, e.g. LÄS MER

  4. 13. Education for Sustainability Leadership : Supporting and empowering agents for sustainability transformations

    Författare :Jayne Bryant; Göran Broman; Merlina Missimer; Edith Callaghan; Arjen Wals; Blekinge Tekniska Högskola; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Education for Sustainable Development; Sustainability Leadership; Sustainability Transformations; Transformative Learning; Systems Change; Strategic Sustainable Development; Strategic Sustainable Development; Strategisk hållbar utveckling;

    Sammanfattning : The global challenges of our time are unprecedented and urgent action for transformation is needed of our systems, policies, institutions and ways of thinking. Education of sustainability leaders is one of the key leverage points to achieve this and many claim that learning on an individual, organisational and societal scale is required for society’s successful transitioning towards sustainability. LÄS MER

  5. 14. Robot Learning for Deformable Object Manipulation Tasks

    Författare :Rita Laezza; Chalmers tekniska högskola; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Deformable Object Manipulation; Deformable Linear Objects; Robotics; Reinforcement Learning; Machine Learning; Robot Learning;

    Sammanfattning : Deformable Object Manipulation (DOM) is a challenging problem in robotics. Until recently, there has been limited research on the subject, with most robotic manipulation methods being developed with rigid objects in mind. LÄS MER

  7. 15. Embodied Evolution of Learning Ability

    Författare :Stefan Elfwing; Henrik Christensen; Jarmo Alander; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Embodied Evolution; Evolutionary Robotics; Reinforcement Learning; Shaping Rewards; Meta-parameters; Hierarchical Reinforcement Learning; Computer science; Datalogi;

    Sammanfattning : 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. LÄS MER