Sökning: "Reward learning"

Visar resultat 1 - 5 av 67 avhandlingar innehållade orden Reward learning.

  1. 1. Learning in Collaboration : Academics’ experiences in collaborative partnerships

    Författare :Jan Karlsson; Elsie Anderberg; Shirley Booth; Per Odenrick; Pedagogik; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; multidisciplinary; SMARTA; krAft; Sweden; NIWL; holistic learning of scholarship; scholarship; interactive research; service; collaboration; Learning; SMEs; academia; Education; Pedagogik; SMARTA; multidisciplinary; krAft; Sweden; NIWL; holistic learning of scholarship; scholarship; interactive research; service; collaboration; Learning; SMEs; academia;

    Sammanfattning : There is an ongoing debate both in the United States and Europe about the need to develop a broader view of scholarship and the different activities connected with it, including “service to the community”. In Sweden, service takes the form of practice-oriented engagement and collaboration with the surrounding community, as stipulated by Swedish law regulating universities’ activities. LÄS MER

  3. 2. Learning from Interactions : Forward and Inverse Decision-Making for Autonomous Dynamical Systems

    Författare :Inês de Miranda de Matos Lourenço; Bo Wahlberg; Sandra Hirche; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Intelligent systems; autonomous decision-making; Reinforcement Learning; Markov models; Human-Robot Interaction; Biologically-inspired systems; Electrical Engineering; Elektro- och systemteknik;

    Sammanfattning : Decision-making is the mechanism of using available information to generate solutions to given problems by forming preferences, beliefs, and selecting courses of action amongst several alternatives. In this thesis, we study the mechanisms that generate behavior (the forward problem) and how their characteristics can explain observed behavior (the inverse problem). LÄS MER

  4. 3. A study of wireless communications with reinforcement learning

    Författare :Wanlu Lei; Ming Xiao; Chenguang Lu; Mikael Skoglund; Geoffrey Ye Li; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Reinforcement learning; wireless communications; decentralized learning; beam tracking; machine learning; Förstärkningsinlärning; trådlös kommunikation; decentrali- serad inlärning; strålspårning i mmvåg; maskininlärning; Electrical Engineering; Elektro- och systemteknik;

    Sammanfattning :  The explosive proliferation of mobile users and wireless data traffic in recent years pose imminent challenges upon wireless system design. The trendfor wireless communications becoming more complicated, decentralized andintelligent is inevitable. LÄS MER

  5. 4. Exploring the bits and pieces of curiosity : an information-theoretic approach to understanding what compels information-seeking

    Författare :Gustaf Wadenholt; Linus Holm; Paul Schrater; Ronald van den Berg; Kou Murayama; Umeå universitet; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Curiosity; uncertainty; information seeking; information gaps; learning satisfaction; learning reward; extrinsic reward; distraction; Psychology; psykologi;

    Sammanfattning : The aim of this thesis is to investigate the computational mechanisms that drive curiosity, the motivational state for learning for its own sake. Curiosity is operationalized as information-seeking behaviors and self-reported curiosity. LÄS MER

  7. 5. If only I could sleep, maybe I could remember

    Författare :Frida H Rångtell; Christian Benedict; Ti­ina Paunio; Uppsala universitet; []
    Nyckelord :MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Sleep; Memory; Learning; Motor skills; Praise; Reward; Sleep deprivation; Sex-differences; LED-screens; Circadian rhythm; Competence-based self-esteem;

    Sammanfattning : Memory lies the ground for human cognitive skills, enabling complex social interaction, abstract thinking, and execution of precise motor skills. Development of these memory functions can be modified by several factors, including previous knowledge, reward, and sleep. LÄS MER