Name: Lukas Schäfer
Type: User
Company: University of Edinburgh
Bio: PhD Data Science & Artificial Intelligence student at the University of Edinburgh
Twitter: LukasSchaefer96
Location: Edinburgh, United Kingdom
Blog: lukaschaefer.com
Lukas Schäfer's Projects
ASNet implementation in FastDownward using Keras & Tensorflow
C Seam-Carving project for Programming 2 lecture at Saarland University
C project for star maps for the Programming 2 lecture at Saarland University Edit Add topics
Implementing Connect Four in Java with JavaFX
The perfect keyboard layout for all computer scientists.
My personal CV(s)
The official repository of "Decoupling Exploration and Exploitation in Reinforcement Learning" (URL Workshop ICML 2021)
dotfiles for MacOS setup
An extension of the PyMARL codebase that includes additional algorithms and environment support
fish setup
Personal webpage with Hugo
Playing around with JAX as acceleration framework
A launch point for your personal nvim configuration
A multi-agent environment for RL
Dotfiles for Ubuntu with i3, polybar, vim, urxvt, rofi, zsh and more
A suite of test scenarios for multi-agent reinforcement learning.
mips-project of programming 2 lecture at Saarland University
MSc Informatics dissertation project - University of Edinburgh: Curiosity in Multi-Agent Reinforcement Learning
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Gym for multi-agent reinforcement learning
Demonstration code for the "Building a Complete RL System" lecture of the Reinforcement Learning course at the University of Edinburgh
Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment
partial interpreter of functional programming language SML, written in SML
A Hugo theme for personal portfolio
VMAS is a vectorized framework designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.