Quality and Diversity Optimization: A Unifying Modular Framework

By Antoine Cully, Yiannis Demiris. IEEE Transactions on Evolutionary Computation, 2017

326 citations recorded by the source corpus.

The optimization of functions to find the best solution according to one or several objectives has a central role in many engineering and research fields. Recently, a new family of optimization algorithms, named quality-diversity (QD) optimization, has been introduced, and contrasts with classic algorithms. Instead of searching for a single solution, QD algorithms are searching for a large collection of both diverse and high-performing solutions. The role of this collection is to cover the range of possible solution types as much as possible, and to contain the best solution for each type. The contribution of this paper is threefold. First, we present a unifying framework of QD optimization algorithms that covers the two main algorithms of this family (multidimensional archive of phenotypic elites and the novelty search with local competition), and that highlights the large variety of variants that can be investigated within this family. Second, we propose algorithms with a new selection mechanism for QD algorithms that outperforms all the algorithms tested in this paper. Lastly, we present a new collection management that overcomes the erosion issues observed when using unstructured collections. These three contributions are supported by extensive experimental comparisons of QD algorithms on three different experimental scenarios.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/1252ce88d42db2810de848e10f0a2d85f9bfdf7b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics (2020, unknown): “Our approach [73] uses a Quality-Diversity (QD) algorithm [77, 78] to build such a skill repertoire, and a generalization approach based on a local linear model of the mapping from the action parameter space to the outcome space to adapt those skills to real robot control.”
Reset-free Trial-and-Error Learning for Robot Damage Recovery (2016, methodology): “e reward function of the MDP. Essentially, MAP-Elites discretizes the n a-dimensional task space to an n a-dimensional grid, and then attempts to ll each of the cells using a variation-selection loop [44, 7, 47]. Algorithmically, it starts with Grandom parameter vectors, simulates the robot with the”
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms (2017, methodology): “Finally, evolutionary and developmental exploration meth-ods like GEP , Novelty Search or Quality-Diversity take advantage of a behavioral features space, which in most works characterizes properties of the state or state-action trajectories.”
Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation (2023, background): “Frameworks unifying quality and diversity optimization can guarantee the diversity of generated solutions that may later serve in robotics to learn behaviorally diverse policies [73].”