Distributed implementation of popular evolutionary methods

Master project

A new version of world models using Echo-state networks and random weight-fixed CNNs

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).

Deep learning and evolutionary algorithms for identification of aerodynamic parameters

Convert images into low poly, using an optimizer

CMA-ES optimization for quantum dot tuning with AutoDot and ModelDot

Python implementation of Regulated Evolution Strategies with Covariance Matrix Adaption for continuous "Black-Box" optimization problems.

(EvoApps2022) "Towards a Principled Learning Rate Adaptation for Natural Evolution Strategies"

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

Official implementation of the MM'21 paper "Constrained Graphic Layout Generation via Latent Optimization" (LayoutGAN++, CLG-LO, and Layout evaluation)

Reproduce the results of "Neuroevolution of Self-Interpretable Agents" paper

Code for: Transforming and Projecting Images into Class-conditional Generative Networks

(CEC2022) Fast Moving Natural Evolution Strategy for High-Dimensional Problems

(GECCO 2022) CMA-ES with Margin: Lower-Bounding Marginal Probability for Mixed-Integer Black-Box Optimization

LLaMA-ES: Tuning CMA-ES hyperparameters using LLaMA3 for optimized numerical function performance.

A personal Python project using Expectimax and CMA-ES to optimise the 2048 game.

Implementation of Farm Surveillance Problem introduced in Optimizing Camera Placement for Chicken Farm Monitoring

Black Box Optimizers for Complex Systems