# Learning and evolution: factors influencing an effective combination

arXiv: https://arxiv.org/abs/2306.11761 · HTML: https://mlsanity.com/paper/2306.11761/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 117 references that are in the map.
- First posted on arXiv 20 Jun 2023.

## Builds on (most cited first, 10 of 10)

- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks](https://mlsanity.com/paper/1703.10371/) (2017)
- [Efficacy of Modern Neuro-Evolutionary Strategies for Continuous Control Optimization](https://mlsanity.com/paper/1912.05239/) (2019)
- [Robust Optimization through Neuroevolution](https://mlsanity.com/paper/1810.01125/) (2018)
- [Robustness, Evolvability and Phenotypic Complexity: Insights from Evolving Digital Circuits](https://mlsanity.com/paper/1712.04254/) (2017)
- [Long-Term Progress and Behavior Complexification in Competitive Co-Evolution](https://mlsanity.com/paper/1909.08303/) (2019)
- [The Dynamic of Body and Brain Co-Evolution](https://mlsanity.com/paper/2011.11440/) (2020)
- [The Role of Morphological Variation in Evolutionary Robotics: Maximizing Performance and Robustness](https://mlsanity.com/paper/2208.02809/) (2022)
- [Memetic Algorithms Beat Evolutionary Algorithms on the Class of Hurdle Problems](https://mlsanity.com/paper/1804.06173/) (2018)
- [Lamarckian Evolution of Convolutional Neural Networks](https://mlsanity.com/paper/1806.08099/) (2018)

## Abstract (arXiv)

The mutual relationship between evolution and learning is a controversial argument among the artificial intelligence and neuro-evolution communities. After more than three decades, there is still no common agreement on the matter. In this paper the author investigates whether combining learning and evolution permits to find better solutions than those discovered by evolution alone. More specifically, the author presents a series of empirical studies that highlight some specific conditions determining the success of such a combination, like the introduction of noise during the learning and selection processes. Results are obtained in two qualitatively different domains, where agent/environment interactions are minimal or absent.