This project makes use of and extends the open source Robogen platform for the simulated co-evolution of collective behavior and morphology.

Interpretable Multi Agent Reinforcement Learning with a Quality DIversity Approach

Implementation of MAP-Elites and Differential Evolution for mobile robotics. Bachelor's Degree Final Project.

MAP-Elites Enemy Generator.

MAP-Elites Level Generator.

Report for my MSc individual project at Imperial College London

Map Elites Hyper-Heuristic based algorithm for generating schedules for the Resource Constrained Project Scheduling Problem

MSc research project on application of Quality-Diversity algorithms for crystal structure prediction

Source code used in simulations for the paper "A Framework for Automatic Behavior Generation in Multi-Function Swarms" accepted by Frontiers in Robotics and AI Oct. 2020.

Co-optimization of body and control of soft robots promoting quality diversity

A universal supervisor controller and ER suite for Webots that can be adapted to any wheeled robot morphology with ease. The project is also setup to allow for easy Reinforcement Learning experimentation with some select algorithms (CMA-ES, Novlty Search, MAP-Elites) and neural networks (fixed and recurrent).

Argenomic is a quality-diversity (or illumination) algorithm for optimization of small organic molecules.

Official implementation of "Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning"

MAP-Elites Hyper-Heuristic based algorithm for generating schedules for the Resource Constrained Project Scheduling Problem

A collection of papers on divergence and quality diversity

A bare-bones Python library for quality diversity optimization.