---
_id: '19962'
abstract:
- lang: eng
  text: Recent approaches in evolutionary robotics (ER) propose to generate behavioral
    diversity in order to evolve desired behaviors more easily. These approaches require
    the definition of a behavioral distance, which often includes task-specific features
    and hence a priori knowledge. Alternative methods, which do not explicitly force
    selective pressure towards diversity (SPTD) but still generate it, are known from
    the field of artificial life, such as in artificial ecologies (AEs). In this study,
    we investigate how SPTD is generated without task-specific behavioral features
    or other forms of a priori knowledge and detect how methods of generating SPTD
    can be transferred from the domain of AE to ER. A promising finding is that in
    both types of systems, in systems from ER that generate behavioral diversity and
    also in the investigated speciation model, selective pressure is generated towards
    unpopulated regions of search space. In a simple case study we investigate the
    practical implications of these findings and point to options for transferring
    the idea of self-organizing SPTD in AEs to the domain of ER.
author:
- first_name: Heiko
  full_name: Hamann, Heiko
  last_name: Hamann
citation:
  ama: 'Hamann H. Lessons from Speciation Dynamics: How to Generate Selective Pressure
    Towards Diversity. <i>Artificial Life</i>. 2015:464-480. doi:<a href="https://doi.org/10.1162/artl_a_00186">10.1162/artl_a_00186</a>'
  apa: 'Hamann, H. (2015). Lessons from Speciation Dynamics: How to Generate Selective
    Pressure Towards Diversity. <i>Artificial Life</i>, 464–480. <a href="https://doi.org/10.1162/artl_a_00186">https://doi.org/10.1162/artl_a_00186</a>'
  bibtex: '@article{Hamann_2015, title={Lessons from Speciation Dynamics: How to Generate
    Selective Pressure Towards Diversity}, DOI={<a href="https://doi.org/10.1162/artl_a_00186">10.1162/artl_a_00186</a>},
    journal={Artificial Life}, author={Hamann, Heiko}, year={2015}, pages={464–480}
    }'
  chicago: 'Hamann, Heiko. “Lessons from Speciation Dynamics: How to Generate Selective
    Pressure Towards Diversity.” <i>Artificial Life</i>, 2015, 464–80. <a href="https://doi.org/10.1162/artl_a_00186">https://doi.org/10.1162/artl_a_00186</a>.'
  ieee: 'H. Hamann, “Lessons from Speciation Dynamics: How to Generate Selective Pressure
    Towards Diversity,” <i>Artificial Life</i>, pp. 464–480, 2015.'
  mla: 'Hamann, Heiko. “Lessons from Speciation Dynamics: How to Generate Selective
    Pressure Towards Diversity.” <i>Artificial Life</i>, 2015, pp. 464–80, doi:<a
    href="https://doi.org/10.1162/artl_a_00186">10.1162/artl_a_00186</a>.'
  short: H. Hamann, Artificial Life (2015) 464–480.
date_created: 2020-10-08T14:36:25Z
date_updated: 2022-01-06T06:54:17Z
department:
- _id: '63'
- _id: '238'
doi: 10.1162/artl_a_00186
language:
- iso: eng
page: 464-480
publication: Artificial Life
publication_identifier:
  issn:
  - 1064-5462
  - 1530-9185
publication_status: published
status: public
title: 'Lessons from Speciation Dynamics: How to Generate Selective Pressure Towards
  Diversity'
type: journal_article
user_id: '15415'
year: '2015'
...
---
_id: '20177'
abstract:
- lang: eng
  text: One of the main challenges in automatic controller synthesis is to develop
    methods that can successfully be applied for complex tasks. The difficulty is
    increased even more in the case of settings with multiple interacting agents.
    We apply the artificial homeostatic hormone system (AHHS) approach, which is inspired
    by the signaling network of unicellular organisms, to control a system of several
    independently acting agents decentrally. The approach is designed for evaluation-minimal,
    artificial evolution in order to be applicable to complex modular robotics scenarios.
    The performance of AHHS controllers is compared with neuroevolution of augmenting
    topologies (NEAT) in the coupled inverted pendulums benchmark. AHHS controllers
    are found to be better for multimodular settings. We analyze the evolved controllers
    with regard to the usage of sensory inputs and the emerging oscillations, and
    we give a nonlinear dynamics interpretation. The generalization of evolved controllers
    to initial conditions far from the original conditions is investigated and found
    to be good. Similarly, the performance of controllers scales well even with module
    numbers different from the original domain the controller was evolved for. Two
    reference implementations of a similar controller approach are reported and shown
    to have shortcomings. We discuss the related work and conclude by summarizing
    the main contributions of our work.
author:
- first_name: Heiko
  full_name: Hamann, Heiko
  last_name: Hamann
- first_name: Thomas
  full_name: Schmickl, Thomas
  last_name: Schmickl
- first_name: Karl
  full_name: Crailsheim, Karl
  last_name: Crailsheim
citation:
  ama: Hamann H, Schmickl T, Crailsheim K. A Hormone-Based Controller for Evaluation-Minimal
    Evolution in Decentrally Controlled Systems. <i>Artificial Life</i>. 2012;18(2):165-198.
    doi:<a href="https://doi.org/10.1162/artl_a_00058">10.1162/artl_a_00058</a>
  apa: Hamann, H., Schmickl, T., &#38; Crailsheim, K. (2012). A Hormone-Based Controller
    for Evaluation-Minimal Evolution in Decentrally Controlled Systems. <i>Artificial
    Life</i>, <i>18</i>(2), 165–198. <a href="https://doi.org/10.1162/artl_a_00058">https://doi.org/10.1162/artl_a_00058</a>
  bibtex: '@article{Hamann_Schmickl_Crailsheim_2012, title={A Hormone-Based Controller
    for Evaluation-Minimal Evolution in Decentrally Controlled Systems}, volume={18},
    DOI={<a href="https://doi.org/10.1162/artl_a_00058">10.1162/artl_a_00058</a>},
    number={2}, journal={Artificial Life}, author={Hamann, Heiko and Schmickl, Thomas
    and Crailsheim, Karl}, year={2012}, pages={165–198} }'
  chicago: 'Hamann, Heiko, Thomas Schmickl, and Karl Crailsheim. “A Hormone-Based
    Controller for Evaluation-Minimal Evolution in Decentrally Controlled Systems.”
    <i>Artificial Life</i> 18, no. 2 (2012): 165–98. <a href="https://doi.org/10.1162/artl_a_00058">https://doi.org/10.1162/artl_a_00058</a>.'
  ieee: H. Hamann, T. Schmickl, and K. Crailsheim, “A Hormone-Based Controller for
    Evaluation-Minimal Evolution in Decentrally Controlled Systems,” <i>Artificial
    Life</i>, vol. 18, no. 2, pp. 165–198, 2012.
  mla: Hamann, Heiko, et al. “A Hormone-Based Controller for Evaluation-Minimal Evolution
    in Decentrally Controlled Systems.” <i>Artificial Life</i>, vol. 18, no. 2, 2012,
    pp. 165–98, doi:<a href="https://doi.org/10.1162/artl_a_00058">10.1162/artl_a_00058</a>.
  short: H. Hamann, T. Schmickl, K. Crailsheim, Artificial Life 18 (2012) 165–198.
date_created: 2020-10-22T09:51:39Z
date_updated: 2022-01-06T06:54:21Z
department:
- _id: '63'
- _id: '238'
doi: 10.1162/artl_a_00058
intvolume: '        18'
issue: '2'
language:
- iso: eng
page: 165-198
publication: Artificial Life
publication_identifier:
  issn:
  - 1064-5462
  - 1530-9185
publication_status: published
status: public
title: A Hormone-Based Controller for Evaluation-Minimal Evolution in Decentrally
  Controlled Systems
type: journal_article
user_id: '15415'
volume: 18
year: '2012'
...