Back to Search
Start Over
Immuno-inspired management of halls of fame for embodied evolution.
- Source :
- Swarm & Evolutionary Computation; Apr2022, Vol. 70, pN.PAG-N.PAG, 1p
- Publication Year :
- 2022
-
Abstract
- Evolutionary robotics employs unconventional techniques to continuously evolve controllers for robots, based on their fitness values. In most cases, a parent controller is subjected to mutation to evolve its offspring. If the offspring performs better than the parent, the former is made to replace the latter. This essentially results in a major loss in information learned by the parents over generations. One simple workaround to circumvent this problem is to maintain a Hall of Fame (HoF) comprising the best parent controllers for use in future generations. In embodied evolutionary robotic scenarios, caching a large number of controllers in an HoF would result in increased computational overheads while selecting the best out of them, resulting in a drastic reduction in performance. With no means to find an upper limit to the number of controllers that can populate an HoF a priori , devising a technique to dynamically regulate this population is imperative. In this work, a novel method to evict the non-performing controllers within an HoF based on the dynamics of the system, is proposed. We describe the evolution of such controllers using genetic operators that eventually form an Idiotypic Network. A constantly varying Resource , associated with each controller together with its concentration in the Idiotypic Network, helps decide its eviction from the HoF. Experiments performed using simulations and also a real robot indicate a marked improvement in the learning process due to the dynamic eviction policy. [ABSTRACT FROM AUTHOR]
- Subjects :
- HALLS of fame
SYSTEM dynamics
EVICTION
ROBOTS
ROBOTICS
Subjects
Details
- Language :
- English
- ISSN :
- 22106502
- Volume :
- 70
- Database :
- Supplemental Index
- Journal :
- Swarm & Evolutionary Computation
- Publication Type :
- Academic Journal
- Accession number :
- 155976091
- Full Text :
- https://doi.org/10.1016/j.swevo.2022.101054