Dynamic State Aggregation

Dynamic State Aggregation is a computational method in reinforcement learning and decision-making systems that dynamically groups or partitions environmental states into aggregated representations based on evolving temporal or structural dependencies, thereby distinguishing itself from static or pre-defined state aggregation techniques by adapting to non-stationary dynamics in real time.

8

Publications

211

Citations

38

Authors

18

Institutions

Publications per year

2017–2026

3

Authors

38

  1. HZ
    Hao Zhang

    Jilin University, China

    1 publications · 34 citations

    1

    h-index

  2. AI
    Anita Ignatius

    Universität Ulm, Germany

    1 publications · 17 citations

    1

    h-index

  3. RQ
    Ruifang Qin

    Columbia University, United States

    1 publications · 17 citations

    1

    h-index

  4. LW
    Li Wang

    Beihang University, China

    1 publications · 40 citations

    1

    h-index

  5. AB
    Alberto Berizzi

    Politecnico di Milano, Italy

    1 publications · 40 citations

    1

    h-index

1–5 of 38

Venues

  1. Energy

    1 publications · 40 citations

    1

    h-index

  2. IFAC Proceedings Volumes

    1 publications · 15 citations

    1

    h-index

  3. Journal of the American Chemical Society

    JACS · 1 publications · 54 citations

    1

    h-index

  4. Operations Research Letters

    1 publications · 17 citations

    1

    h-index

  5. Macromolecules

    1 publications · 34 citations

    1

    h-index

1–5