# On the use of feature-maps and parameter control for improved quality-diversity meta-evolution

arXiv: https://arxiv.org/abs/2105.10317 · HTML: https://mlsanity.com/paper/2105.10317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 40 references that are in the map.
- First posted on arXiv 21 May 2021.

## Builds on (most cited first, 6 of 6)

- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors](https://mlsanity.com/paper/1905.11874/) (2019)
- [Hierarchical Behavioral Repertoires with Unsupervised Descriptors](https://mlsanity.com/paper/1804.07127/) (2018)
- [QED: using Quality-Environment-Diversity to evolve resilient robot swarms](https://mlsanity.com/paper/2003.02341/) (2020)

## Abstract (arXiv)

In Quality-Diversity (QD) algorithms, which evolve a behaviourally diverse archive of high-performing solutions, the behaviour space is a difficult design choice that should be tailored to the target application. In QD meta-evolution, one evolves a population of QD algorithms to optimise the behaviour space based on an archive-level objective, the meta-fitness. This paper proposes an improved meta-evolution system such that (i) the database used to rapidly populate new archives is reformulated to prevent loss of quality-diversity; (ii) the linear transformation of base-features is generalised to a feature-map, a function of the base-features parametrised by the meta-genotype; and (iii) the mutation rate of the QD algorithm and the number of generations per meta-generation are controlled dynamically. Experiments on an 8-joint planar robot arm compare feature-maps (linear, non-linear, and feature-selection), parameter control strategies (static, endogenous, reinforcement learning, and annealing), and traditional MAP-Elites variants, for a total of 49 experimental conditions. Results reveal that non-linear and feature-selection feature-maps yield a 15-fold and 3-fold improvement in meta-fitness, respectively, over linear feature-maps. Reinforcement learning ranks among top parameter control methods. Finally, our approach allows the robot arm to recover a reach of over 80% for most damages and at least 60% for severe damages.