Sven Gronauer's Projects
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Create clusters and train models in distributed fashion
An easy way to extract information from documents
Refer to https://github.com/AcutronicRobotics/gym-gazebo2 for the new version
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Simulation environments for the CrazyFlie quadrotor: Used for Reinforcement Learning and Sim-to-Real Transfer
Poppy Humanoid is an open-source and 3D printed humanoid robot. Optimized for research and education purposes, its modularity allows for a wide range of applications and experimentations.
Open-source implementations of OpenAI Gym MuJoCo environments for use with the OpenAI Gym Reinforcement Learning Research Platform.
Implementations of safe reinforcement learning algorithms
rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
Python library to decode StarCraft II replay protocols
Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
Extracts gameplay information from Starcraft II replay files
Submission to The 2nd e-Prevention Challenge: Psychotic and Non-Psychotic Relapse Detection using Wearable-Based Digital Phenotyping
Building arbitrarily deep models of Spiking Convolutional Neural Networks on SpiNNaker
Code of the Paper "The Successful Ingredients of Policy Gradient Algorithms"
Personal Website
A personalized neural network toolbox for research purposes. Built upon the TensorFlow 2.0alpha framework and TensorFlow's Keras.
Ensemble Model Predictive Safety Certification