biemann
I am interested in mathematics, reinforcement learning and theoretical machine learning. Currently Phd Student at DTU in Denmark
Copenhagen, Denmark
Pinned Repositories
biemann.github.io
Collaboration-and-Competition
Third project for the Udacity Nanodegree in Deep Reinforcement Learning. It is a multi-agent system, where two independently trained agents need to collaborate for solving a test as well as possible.
Continuous-Control
Deep Reinforcement Learning Nanodegree project on continuous control, based on the DDPG algorithm.
Navigation
Navigation project in Deep Reinforcement Learning (Udacity course), using the Q-learning algorithm.
Projects_Extension_School
This repository contains 5 projects I did while working towards the Certificate of Open Studies from EPFL Extension School in Lausanne, Switzerland.
rl-testbed-for-energyplus
Reinforcement Learning Testbed for Power Consumption Optimization using EnergyPlus
sinergym
Gym environment for building simulation and control using reinforcement learning
stable-baselines3
PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.
tropical_precooling_environment
Eine Simulationsumgebung zur Evaluierung und Bechmarking von Algorithmen zur Gebäudeenergieoptimierung.
sinergym
Gym environment for building simulation and control using reinforcement learning
biemann's Repositories
biemann/Continuous-Control
Deep Reinforcement Learning Nanodegree project on continuous control, based on the DDPG algorithm.
biemann/biemann.github.io
biemann/Collaboration-and-Competition
Third project for the Udacity Nanodegree in Deep Reinforcement Learning. It is a multi-agent system, where two independently trained agents need to collaborate for solving a test as well as possible.
biemann/Navigation
Navigation project in Deep Reinforcement Learning (Udacity course), using the Q-learning algorithm.
biemann/Projects_Extension_School
This repository contains 5 projects I did while working towards the Certificate of Open Studies from EPFL Extension School in Lausanne, Switzerland.
biemann/rl-testbed-for-energyplus
Reinforcement Learning Testbed for Power Consumption Optimization using EnergyPlus
biemann/sinergym
Gym environment for building simulation and control using reinforcement learning
biemann/stable-baselines3
PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.
biemann/tropical_precooling_environment
Eine Simulationsumgebung zur Evaluierung und Bechmarking von Algorithmen zur Gebäudeenergieoptimierung.