Batsim is a scientific simulator commonly used to evaluate Resource and Job Management System (RJMS) policies. Batsim-py allows using Batsim from Python 3.

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Nix expressions related to HPC and Distributed Systems research domains

Batsim: Infrastructure simulator for job and I/O scheduling

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

[AAAI-23] Improving Pareto Front Learning via Multi-Sample Hypernetworks

Source code for "A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning" (ICML 2021)

Experiments of the paper "Hessian Aided Policy Gradient"

Implementation of "Exponential Natural Evolution Strategies" (xNES) https://arxiv.org/abs/1106.4487

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

Python Data. Leaflet.js Maps.

Evolution Strategies in PyTorch

Implementation of "Learning Combinatorial Optimization Algorithms over Graphs"

Official implementation of Learning The Pareto Front With HyperNetworks [ICLR 2021]

Deep Reinforcement Learning for Multiobjective Optimization. Code for this paper

Source code for the dissertation: "Multi-Pass Deep Q-Networks for Reinforcement Learning with Parameterised Action Spaces"

Evolutionary multi-objective optimization platform

Deep Reinforcement Learning by using Proximal Policy Optimization and Random Network Distillation in Tensorflow 2 and Pytorch with some explanation

Coding Demos from the School of AI's Move37 Course

NSGA2, NSGA3, R-NSGA3, MOEAD, Genetic Algorithms (GA), Differential Evolution (DE), CMAES, PSO

The Go programming language