Evolving the Behavior of Machines: From Micro to Macroevolution
arXiv:2012.11692 · doi:10.1016/j.isci.2020.101731
Abstract
Evolution gave rise to creatures that are arguably more sophisticated than the greatest human-designed systems. This feat has inspired computer scientists since the advent of computing and led to optimization tools that can evolve complex neural networks for machines -- an approach known as "neuroevolution". After a few successes in designing evolvable representations for high-dimensional artifacts, the field has been recently revitalized by going beyond optimization: to many, the wonder of evolution is less in the perfect optimization of each species than in the creativity of such a simple iterative process, that is, in the diversity of species. This modern view of artificial evolution is moving the field away from microevolution, following a fitness gradient in a niche, to macroevolution, filling many niches with highly different species. It already opened promising applications, like evolving gait repertoires, video game levels for different tastes, and diverse designs for aerodynamic bikes.
References in corpus (16)
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Robots that can adapt like animals
- Emergence of Locomotion Behaviours in Rich Environments
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
- The evolutionary origins of modularity
- Illuminating search spaces by mapping elites
- Evolving embodied intelligence from materials to machines
- Procedural Content Generation through Quality Diversity
- Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
- Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space
- Reset-free Trial-and-Error Learning for Robot Damage Recovery
- Discovering the Elite Hypervolume by Leveraging Interspecies Correlation
- Measurement of the top quark mass with dilepton events selected using neuroevolution at CDF
- Evolvability Is Inevitable: Increasing Evolvability Without the Pressure to Adapt
- Scaling MAP-Elites to Deep Neuroevolution
- Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics