LukasSchaefer

MSc_Curiosity_MARL

MSc Informatics dissertation project - University of Edinburgh: Curiosity in Multi-Agent Reinforcement Learning

RL2020_Building-a-Complete-RL-System_Demonstration

Demonstration code for the "Building a Complete RL System" lecture of the Reinforcement Learning course at the University of Edinburgh

multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

ASNets_FastDownward

ASNet implementation in FastDownward using Keras & Tensorflow

jax_playground

Playing around with JAX as acceleration framework

linux_dotfiles

Dotfiles for Ubuntu with i3, polybar, vim, urxvt, rofi, zsh and more

robotic-warehouse

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

SML_Interpreter

partial interpreter of functional programming language SML, written in SML

hugo_website

Personal webpage with Hugo

toha

A Hugo theme for personal portfolio

boulderpush

c-seam-carving

C Seam-Carving project for Programming 2 lecture at Saarland University

c_star_project

C project for star maps for the Programming 2 lecture at Saarland University Edit Add topics

ConnectFour

Implementing Connect Four in Java with JavaFX

CSKey

The perfect keyboard layout for all computer scientists.

CV

My personal CV(s)

derl

The official repository of "Decoupling Exploration and Exploitation in Reinforcement Learning" (URL Workshop ICML 2021)

dotfiles

dotfiles for MacOS setup

fish

fish setup

lb-foraging

A multi-agent environment for RL

meltingpot

A suite of test scenarios for multi-agent reinforcement learning.

mips_project

mips-project of programming 2 lecture at Saarland University

PettingZoo

Gym for multi-agent reinforcement learning

VectorizedMultiAgentSimulator

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.