R

reinforcement learning

Code and model data for article titled "Predicting Driver Adaptability: A Computational Rationality Model for Attention Allocation in Lateral Vehicle Control" (Hautaoja, 2025).

Modernised fork of ns3-ai (Yin et al., WNS3 2020): ns-3.43 + Python 3.13 + NumPy 2 + Gymnasium 1.0 compatibility patches for the shared-memory C++/Python bridge. Adds NTN Gym environments and a Flower AI federated-learning adaptor (FedAvg/Prox/Nova/SCAFFOLD). Upstream credit preserved in AUTHORS.md. GPL-2.0.

The VGC AI Framework aims to emulate the Esports scenario of human video game championships of Pokémon with AI agents, including the game balance aspect.

Transfer learning application in reinforcement learning

Simple DQN (Deep Q-Network) implementation for CartPole

MSc degree thesis: multi-agent reinforcement learning for workload distribution in FaaS edge computing systems

This project provides optimal control and reinforcement learning implementations to optimize vaccination and testing resource allocation problems on networks.

Lifelong learning is a complex topic in machine learning, whether in combination with reinforce- ment learning or other learning methods. There are different approaches for this and one of them are hypernetworks. Hypernetworks have the advantage of having a very large ability to preserve past memories. Recent work attempts to demonstrate the learning ability of multiple tasks with a hypernetwork such as in the combination of reinforcement learning.

Project for the 2024 Multi-agent Reinforcement Learning course, at the University of Groningen. Contains PPO-based CTDE and CTCE methods that work really well.

This project adopts Reinforcement Learning to solve a variant of the stochastic VRP, where customers are highly variable, demands are stochastic, and vehicles have a duration limit.

PhD work by Jonathan Brady on utilizing reinforcement learning to grow implicit primitives towards attractor points.

The code in this repository is used for the research on multi-agent reinforcement learning for power grids of Erica van der Sar. The results in the paper "Multi-Agent Reinforcement Learning for Power Grid Topology Optimization" (https://doi.org/10.48550/arXiv.2310.02605) are produced using this code base.

A game where we gonna train an IA with the Q-Learning to be able to play on the famous "Flappy Bird" game.

Program analysis-based optimization in differentiable simulators.

An RL framework for multiplayer dynamic difficulty adjustment.

The Simple Pokémon Environment is an AI environment complient with gym that allows for training Reinforcement Learning agents in a simplified version of Pokémon Battles.

Stage de fin d'étude sur le développement d'un modèle d'apprentissage par renforcement multi-objectifs pour répondre à des problèmes éthiques.

Encadrants : Aurélie Beynier, Nicolas Maudet, Paolo Viappiani Date : Mars - Septembre 2022

Example of CartPole task solution with random search, noise hill-climbing, Q-net training and policy gradient approaches.

Use play_result.py to visualize result.

Solution of Cliff Walking problem with different variants of Q-learning and SARSA algorithms.

Simple example of FrozenLake task solution with value/strategy iteration, Monte-Carlo methods and with genetic algorithm.