Evolutionary Neural Controllers

Evolutionary Neural Controllers is a computational framework within evolutionary robotics that employs evolutionary algorithms to automatically design and optimize neural network-based control systems for autonomous agents, distinguishing itself from traditional control methods by enabling adaptive, task-specific behavioral learning through simulated natural selection.

313

Publications

14.3K

Citations

615

Authors

290

Institutions

Publications per year

2017–2026

49

Authors

615

  1. DF
    Dario Floreano

    École Polytechnique Fédérale de Lausanne, Switzerland

    18 publications · 2K citations

    18

    h-index

  2. SN
    Stefano Nolfi

    Institute of Cognitive Sciences and Technologies, Italy

    11 publications · 1.1K citations

    10

    h-index

  3. PH
    Phil Husbands

    University of Sussex, United Kingdom

    9 publications · 520 citations

    9

    h-index

  4. AL
    Anders Lyhne Christensen

    Iscte – Instituto Universitário de Lisboa, Portugal

    8 publications · 362 citations

    8

    h-index

  5. JT
    Julian Togelius

    New York University, United States

    8 publications · 378 citations

    8

    h-index

1–5 of 615

Venues

  1. Adaptive Behavior

    10 publications · 962 citations

    10

    h-index

  2. Robotics and Autonomous Systems

    8 publications · 267 citations

    8

    h-index

  3. Artificial Life

    8 publications · 840 citations

    8

    h-index

  4. Connection Science

    7 publications · 353 citations

    7

    h-index

  5. Neurocomputing

    5 publications · 99 citations

    5

    h-index

1–5