Concepedia

Multi-objective Temporal Difference Learning

Multi-Objective Temporal Difference Learning is a reinforcement learning method that extends classical Temporal Difference Learning to handle multiple conflicting objectives by learning a set of value functions or policies that approximate the Pareto optimal frontier in stochastic environments modeled as Multi-Objective Markov Decision Processes.

13

Publications

1.6K

Citations

22

Authors

17

Institutions

Publications per year

2017–2026

2

Parents

Publications

13

Practical issues in temporal difference learning

Gerald Tesauro · Machine Learning · 1992 · 800 citations · Full text

, , +7

Multi-objective reinforcement learning using sets of pareto dominating policies

Kristof Van Moffaert, Ann Nowé · 2014 · 240 citations

, , +14

Average cost temporal-difference learning

John N. Tsitsiklis, Benjamin Van Roy · Automatica · 1999 · 142 citations

, , +4

Ant-TD: Ant colony optimization plus temporal difference reinforcement learning for multi-label feature selection

Mohsen Paniri, Mohammad Bagher Dowlatshahi, Hossein Nezamabadi–pour · Swarm and Evolutionary Computation · 2021 · 128 citations

, , +10

Sequential anomaly detection based on temporal-difference learning: Principles, models and case studies

Xin Xu · Applied Soft Computing · 2009 · 68 citations

, , +12

1–5 of 13

Authors

22

  1. GT
    Gerald Tesauro

    IBM (United States), United States

    2 publications · 839 citations

    2

    h-index

  2. JN
    John N. Tsitsiklis

    Massachusetts Institute of Technology, United States

    2 publications · 172 citations

    2

    h-index

  3. AN
    Ann Nowé

    Vrije Universiteit Brussel, Belgium

    2 publications · 276 citations

    2

    h-index

  4. BV
    Benjamin Van Roy

    Stanford University, United States

    2 publications · 172 citations

    2

    h-index

  5. MP
    Mohsen Paniri

    Lorestan University, Iran

    1 publications · 128 citations

    1

    h-index

1–5 of 22

Institutions

17

  1. IBM Research - Thomas J. Watson Research Center

    Yorktown Heights, United States

    2 h-index

    2 publications

    839 citations

  2. Massachusetts Institute of Technology

    Cambridge, United States

    2 h-index

    4 publications

    344 citations

  3. Vrije Universiteit Brussel

    Brussels, Belgium

    2 h-index

    4 publications

    552 citations

  4. Lorestan University

    Khorramabad, Iran

    1 h-index

    2 publications

    256 citations

  5. Université Constantine 2

    Constantine, Algeria

    1 h-index

    1 publications

    18 citations

  6. Institute of Automation

    Beijing, China

    1 h-index

    1 publications

    68 citations

  7. Decision Systems (United States)

    Northbrook, United States

    1 h-index

    2 publications

    60 citations

  8. The University of Tokyo

    Tokyo, Japan

    1 h-index

    1 publications

    22 citations

1–8 of 17

Venues

  1. Machine Learning

    2 publications · 839 citations

    2

    h-index

  2. Applied Soft Computing

    1 publications · 68 citations

    1

    h-index

  3. Evolving Systems

    1 publications · 18 citations

    1

    h-index

  4. Automatica

    1 publications · 142 citations

    1

    h-index

  5. Bulletin of Mathematical Biology

    1 publications · 22 citations

    1

    h-index

1–5