Multi-step Exploration

Multi-Step Exploration is a sequential decision-making strategy within reinforcement learning that systematically extends exploration over multiple time steps to balance the acquisition of new information with the refinement of policy performance, distinguishing itself from single-step methods by considering the long-term impact of exploratory actions.

12

Publications

355

Citations

37

Authors

21

Institutions

Publications per year

2017–2026

8

Authors

37

  1. AC
    Anne Collins

    University of California, Berkeley, United States

    2 publications · 44 citations

    2

    h-index

  2. TP
    Thomas Price

    North Carolina State University, United States

    2 publications · 43 citations

    2

    h-index

  3. LX
    Liyu Xia

    University of California, Berkeley, United States

    2 publications · 44 citations

    2

    h-index

  4. NP
    Niels Pinkwart

    Humboldt-Universität zu Berlin, Germany

    2 publications · 43 citations

    2

    h-index

  5. BH
    Barbara Hammer

    Bielefeld University, Germany

    2 publications · 43 citations

    2

    h-index

1–5 of 37

Venues

  1. arXiv (Cornell University)

    Repository · 2 publications · 63 citations

    2

    h-index

  2. Psychological Review

    1 publications · 32 citations

    1

    h-index

  3. Zenodo (CERN European Organization for Nuclear Research)

    Repository · 1 publications · 31 citations

    1

    h-index

  4. IEEE Access

    1 publications · 55 citations

    1

    h-index

  5. bioRxiv (Cold Spring Harbor Laboratory)

    Repository · 1 publications · 12 citations

    1

    h-index

1–5