Name
Abstract | ||
|---|---|---|
An ambitious goal in evolutionary robotics (ER) is to evolve increasingly complex robotic behaviors with minimal human design effort. Reaching this goal requires evolutionary algorithms that can unlock from genetic encodings their latent potential for evolvability. One issue clouding this goal is conceptual confusion about evolvability that often obscures important or desirable aspects of evolvability. The danger from such confusion is that it may establish unrealistic goals for evolvability that prove unproductive in practice. An important issue separate from conceptual confusion is the common misalignment between selection and evolvability in ER. While more expressive encodings can represent higher-level adaptations (e.g. sexual reproduction or developmental systems) that increase long-term evolutionary potential (i.e. evolvability), realizing such potential requires gradients of fitness and evolvability to align. In other words, selection is often a critical factor limiting increasing evolvability. Thus, drawing from a series of recent papers, this article seeks to both (1) clarify and focus the ways in which the term evolvability is used within artificial evolution and (2) argue for the importance of one type of selection, i.e. divergent selection, for enabling evolvability. The main argument is that there is a fundamental connection between divergent selection and evolvability (on both the individual and population level) that does not hold for typical goal-oriented selection. The conclusion is that selection pressure plays a critical role in realizing the potential for evolvability and that divergent selection in particular provides a principled mechanism for encouraging evolvability in artificial evolution. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.3389/frobt.2016.00045 | FRONTIERS IN ROBOTICS AND AI |
Keywords | Field | DocType |
evolutionary robotics,evolvability,divergent selection,encodings,evolution of complexity | Population,Confusion,Evolutionary algorithm,Evolutionary robotics,Cognitive science,Evolvability,Computer science,Artificial intelligence,Limiting,Machine learning | Journal |
Volume | ISSN | Citations |
3.0 | 2296-9144 | 1 |
PageRank | References | Authors |
0.35 | 19 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Joel Lehman | 1 | 40 | 4.81 |
| Bryan Wilder | 2 | 34 | 13.53 |
| Kenneth O. Stanley | 3 | 4347 | 225.49 |