Online Multi-objective Learning

Online Multi-Objective Learning is a sequential decision-making framework within Multi-Objective Markov Decision Processes that dynamically optimizes multiple conflicting objectives in real-time as environmental feedback is incrementally acquired, distinguishing itself by its adaptive policy generation under non-stationary reward structures without prior knowledge of the objective space.

57

Publications

2.9K

Citations

218

Authors

106

Institutions

Publications per year

2017–2026

46

Authors

218

  1. GG
    Gary G. Yen

    Oklahoma State University, United States

    3 publications · 264 citations

    3

    h-index

  2. BS
    Balázs Szörényi

    MTA-SZTE Research Group on Artificial Intelligence, Hungary

    2 publications · 26 citations

    2

    h-index

  3. MM
    Mădălina M. Drugan

    University of Groningen, Netherlands

    2 publications · 134 citations

    2

    h-index

  4. PV
    Peter Vamplew

    Federation University, Australia

    2 publications · 287 citations

    2

    h-index

  5. SM
    Shie Mannor

    Technion – Israel Institute of Technology, Israel

    2 publications · 26 citations

    2

    h-index

1–5 of 218

Venues

  1. Knowledge-Based Systems

    3 publications · 247 citations

    3

    h-index

  2. 3

    h-index

  3. Information Sciences

    3 publications · 202 citations

    3

    h-index

  4. Expert Systems with Applications

    3 publications · 118 citations

    3

    h-index

  5. Computers & Electrical Engineering

    2 publications · 69 citations

    2

    h-index

1–5