Marco Pleines

episodic-transformer-memory-ppo. Clean baseline implementation of PPO using an episodic TransformerXL memory

recurrent-ppo-truncated-bptt. Baseline implementation of recurrent PPO using truncated BPTT

endless-memory-gym. Challenging Memory-based Deep Reinforcement Learning Agents

neroRL. Deep Reinforcement Learning Framework done with PyTorch

Unity-ML-Environments. This repository features game simulations as machine learning environments to experiment with deep learning approaches such as deep reinforcement learning inside of Unity.

StarcraftNeuralNetAi. This is the implementation of my Bachelor Thesis

CIV-ML-Agents-Environments. This repository features Reinforcement Learning environments that are made with Unity ML-Agents to approach industrial use-cases.

Action-Space-Compositions-in-Deep-Reinforcement-Learning. Application of concurrent discrete and continuous actions on two novel DRL environments to mimic human input devices.

Wine-Classification-Course. Using a multi-layer perceptron and the kNN Algorithm to classify wine to be red or white wine.

pokemon_replay_recorder. Just a simple replay recorder

cleanrl-ppo-trxl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Beastly-Rivals-Onslaught. Beastly Rivals Onslaught (BRO) is a use-case for conducting AI research made with Unity.

ml-agents. Unity Machine Learning Agents Toolkit

Simple-Image-Labelling-Tool. SILT is a trivial tool (build with .net 4.6.1) to help labeling images.

Unity-ML-Agents-Docker-Image. This repository provides all the necessary files to build and run a docker container, which is capable of training environments based on Unity's ML-Agents.