Sökning: "reinforcement learning"

Visar resultat 1 - 5 av 69 avhandlingar innehållade orden reinforcement learning.

  1. 1. The reinforcement learning method : A feasible and sustainable control strategy for efficient occupant-centred building operation in smart cities

    Författare :Ross May; Kenneth Carling; Mengjie Han; Pascal Rebreyend; Zoltan Nagy; Högskolan Dalarna; []
    Nyckelord :ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Markov decision processes; Reinforcement learning; Control; Building; Indoor comfort; Occupant; Complex Systems – Microdata Analysis; Komplexa system - mikrodataanalys;

    Sammanfattning : Over half of the world’s population lives in urban areas, a trend which is expected to only grow as we move further into the future. With this increasing trend in urbanisation, challenges are presented in the form of the management of urban infrastructure systems. LÄS MER

  2. 2. Towards Manipulator Learning by Demonstration and Reinforcement Learning

    Författare :Alexander Skoglund; Örebro universitet; []
    Nyckelord :NATURAL SCIENCES; NATURVETENSKAP; NATURVETENSKAP; NATURAL SCIENCES; Manipulation; learning; robot learning from demonstration; programming by demonstration; imitation in robotics.; Computer science; Datavetenskap;

    Sammanfattning : This thesis address how robotic arms, called manipulators, can learn a task demonstrated by a teacher. The concept of showing a robot a task, instead of manually programming it, is appealing since it makes it easier to instruct robots. LÄS MER

  3. 3. Sample Efficient Bayesian Reinforcement Learning

    Författare :Divya Grover; Chalmers University of Technology; []
    Nyckelord :NATURVETENSKAP; NATURVETENSKAP; TEKNIK OCH TEKNOLOGIER; NATURAL SCIENCES; NATURAL SCIENCES; ENGINEERING AND TECHNOLOGY; Decision Making under Uncertainty; Bayesian Reinforcement Learning; Model based Reinforcement Learning;

    Sammanfattning : Artificial Intelligence (AI) has been an active field of research for over a century now. The research field of AI may be grouped into various tasks that are expected from an intelligent agent; two major ones being learning & inference and planning . LÄS MER

  4. 4. Computational Modeling of the Basal Ganglia : Functional Pathways and Reinforcement Learning

    Författare :Pierre Berthet; Anders Lansner; Kenji Doya; Stockholms universitet; []
    Nyckelord :NATURAL SCIENCES; NATURVETENSKAP; NATURVETENSKAP; NATURAL SCIENCES; computational neuroscience; modelisation; reinforcement learning; basal ganglia; dopamine; datalogi; Computer Science;

    Sammanfattning : We perceive the environment via sensor arrays and interact with it through motor outputs. The work of this thesis concerns how the brain selects actions given the information about the perceived state of the world and how it learns and adapts these selections to changes in this environment. LÄS MER

  5. 5. 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 :NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; NATURVETENSKAP; NATURVETENSKAP; SAMHÄLLSVETENSKAP; NATURAL SCIENCES; NATURAL SCIENCES; 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; vetenskap om hållbar utveckling; Sustainability Science;

    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