Automated Machine Learning with scikit-learn

OpenDILab Decision AI Engine

This is the official implementation of Multi-Agent PPO (MAPPO).

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

[AAAI 2023] Official PyTorch implementation of paper "ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency".

Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.

Unofficial open-source OpenGL/SDL2 client for Sid Meier's Alpha Centauri ( + Alien Crossfire )

StarCraft II Multi Agent Challenge : QMIX, COMA, LIIR, QTRAN, Central V, ROMA, RODE, DOP, Graph MIX

Multi-agent PPO with noise (97% win rates on Hard scenarios of SMAC)

[ICML 2021] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Bayesian Optimization for Categorical and Continuous Inputs

Continual Multi-agent Reinforcement Learning in Dynamic Environments

Anti-Cheat Detection for Game Streaming

An automated data augmentation tool in Python

Systematic Evaluation of CASH Search Strategies for Unsupervised Anomaly Detection

Thematic lists of Dutch words which can be used in naming schemes

A library based on Keras, SMAC and HpBandSter to auto tune autoencoder architectures.

In this project, we focus on different ways to optimize a machine learning model parameters.

Research and Development project report. Affliations: Hochschule Bonn-Rhein-Sieg and Fraunhofer SCAI