Author Image

Hi, I am Lukas

Lukas Schäfer

PhD Student at University of Edinburgh

I am a 25-year-old Data Science and Artificial Intelligence PhD student from Germany working on Multi-Agent Reinforcement learning at the University of Edinburgh, where I am supervised by Stefano Albrecht and Amos Storkey.

Currently, I am doing a research internship at Huawei Noah’s Ark Lab (multi-agent team) with David Mguni. Previously, I interned at Dematic where I researched and developed AI solutions for large-scale warehouse automation.

My research focuses on the challenges of generalisation and sample efficiency: how can multiple agents learn effective behaviour with less data and be able to learn robust, re-usable skills which transfer to new environments.

Research
Deep Learning
Teaching
Python
Unix
SE

News

Sep 14, 2022

📃 Our work, Robust On-Policy Sampling for Data-Efficient Policy Evaluation, has been accepted at the Neural Information Processing Systems Conference (NeurIPS) 2022!

Aug 27, 2022

📢 Excited to announce that I was selected to attend the upcoming 9th Heidelberg Laureate Forum!

Jul 05, 2022

Jul 04, 2022

📢 Excited to start a research internship at Huawei Noah’s Ark Lab in London (multi-agent team) with David Mguni!

Feb 10, 2022

📃 My submission on Task Generalisation in Multi-Agent Reinforcement Learning has been accepted in the Doctoral Consortium of the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2022!

Dec 19, 2021

📃 Our work, Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration, has been accepted at International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2022!

Aug 29, 2021

🤖 Just published a big redesign of my webpage based on GoHugo!

Jul 30, 2021

📃 Our work, Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks, has been accepted at the Datasets and Benchmarks track of the Neural Information Processing Systems Conference (NeurIPS) 2021!

Publications

Rujie Zhong, Duohan Zhang, Lukas Schäfer, Stefano V. Albrecht, Josiah P. Hanna (2022)
Conference on Neural Information Processing Systems (NeurIPS), 2022
Lukas Schäfer (2022)
Doctoral Consortium at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022
Lukas Schäfer, Filippos Christianos, Josiah P. Hanna, Stefano V. Albrecht (2022)
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022
Georgios Papoudakis, Filippos Christianos, Lukas Schäfer, Stefano V. Albrecht (2021)
Conference on Neural Information Processing Systems (NeurIPS), 2021 - Datasets and Benchmarks track
Lukas Schäfer, Filippos Christianos, Josiah P. Hanna, Stefano V. Albrecht (2021)
Unsupervised Reinforcement Learning (URL) Workshop in the International Conference on Machine Learning, 2021
Rujie Zhong, Josiah P. Hanna, Lukas Schäfer, Stefano V. Albrecht (2021)
Workshop on Offline Reinforcement Learning in the Conference on Neural Information Processing Systems, 2021
Filippos Christianos, Lukas Schäfer, Stefano V. Albrecht (2020)
Conference on Neural Information Processing Systems (NeurIPS), 2020
Lukas Schäfer, Filippos Christianos, Amos Storkey, Stefano V. Albrecht (2022)
arXiv
Trevor McInroe, Lukas Schäfer, Stefano V. Albrecht (2022)
arXiv
Trevor McInroe, Lukas Schäfer, Stefano V. Albrecht (2021)
arXiv

Experiences

1
Young Research Attendee
Heidelberg Laureate Forum

Sep 2022 - Sep 2022, Heidelberg

The Heidelberg Laureate Forum brings together the most exceptional mathematicians and computer scientists of their generations. Each year, the recipients of the most prestigious awards in mathematics and computer science, the Abel Prize, ACM A.M. Turing Award, ACM Prize in Computing, Fields Medal, IMU Abacus Medal and Nevanlinna Prize, meet 200 selected young researchers from all over the world. Participants spend a week interacting and networking in a relaxed atmosphere designed to encourage scientific exchange.


Research Scientist Intern
Huawei Noah's Ark Lab

Jul 2022 - Present, London

The Noah’s Ark Lab is the AI research center for Huawei Technologies, working towards significant contributions to both the company and society by innovating in artificial intelligence, data mining and related fields.

Responsibilities:
  • Working with the RL and multi-agent team on multi-agent reinforcement learning exploration under the supervision of David Mguni.
2

3
Research Intern
Dematic

Nov 2020 - Mar 2021, Remote

Dematic is global player focused on design and implementation of automated system solutions for warehouses, distribution centres and production facilities.

Responsibilities:
  • Applying state-of-the-art AI technology to enable a prototype for automation of large-scale robotic warehouse logistics.

HYPED

Sep 2018 - Aug 2020, Edinburgh

HYPED is a team of students at the University of Edinburgh dedicated to developing the Hyperloop concept and inspiring future generations about engineering. HYPED has received awards from SpaceX, Virgin Hyperloop One and Institution of Civil Engineers.

Navigation Advisor

Sep 2019 - Aug 2020

  • Advising navigation team on the adaptation and implementation of improved sensor and filtering techniques
Navigation Engineer

Sep 2018 - Aug 2019

  • Developing navigation system of “The Flying Podsman” Hyperloop prototype using sensor filtering, processing and control techniques to estimate location, orientation and speed of the pod
  • Finalist for the SpaceX 2019 Hyperloop competition in California in Summer 2019
4

Education

University of Edinburgh
Ph.D in Data Science and Artificial Intelligence
Project: Sample Efficiency and Generalisation in Multi-Agent Reinforcement Learning
Supervisors: Stefano V. Albrecht (primary) and Amos Storkey (secondary)
Funding: Principal's Career Development Scholarship from the University of Edinburgh
Key Areas: Reinforcement Learning, Multi-Agent Systems, Generalisation, Exploration, Intrinsic Rewards
2019-Present
University of Edinburgh
M.Sc. in Informatics
CGPA: 77.28%
Funding: DAAD (German Academic Exchange Service) graduate scholarship & Stevenson Exchange Scholarship
Taken Courses
Course NameObtained Credit
Reinforcement Learning10 (82%)
Algorithmic Game Theory and its Applications10 (98%)
Machine Learning and Pattern Recognition20 (64%)
Probabilistic Modelling and Reasoning20 (75%)
Decision Making in Robots and Autonomous Agents10 (86%)
Robotics: Science and Systems20 (87%)
Natural Computing10 (84%)
Informatics Project Proposal10 (73%)
Informatics Research Review10 (72%)
Extracurricular Activities
  • Active position as navigation engineer for HYPED.
  • Participation in GEAS roleplaying society.
  • Participation in EUKC - Edinburgh University Kendo Club.
2018-2019
Saarland University
B.Sc. in Informatics
GPA: 3.7
Taken Courses
Course NameObtained Credit
Automated Planning9 (4.0)
Admissible Search Enhancements7 (4.0)
Information Retrieval and Data Mining9 (3.3)
Neural Networks: Implementation and Application6 (2.0)
Artificial Intelligence9 (3.3)
Software Engineering9 (3.7)
Modern Imperative Programming Languages5 (3.7)
Concurrent Programming6 (2.3)
Fundamentals of Data Structures and Algorithms6 (3.3)
Information Systems6 (3.7)
Introduction to Theoretical Computer Science9 (4.0)
System Architecture9 (4.0)
Mathematics for Computer Scientists I9 (4.0)
Mathematics for Computer Scientists II9 (2.7)
Mathematics for Computer Scientists III9 (3.3)
Programming I9 (4.0)
Programming II9 (4.0)
Japanese Foundations - Shokyu I6 (3.7)
Japanese Foundations - Shokyu II6 (3.0)
Japanese Applied Geography5 (4.0)
Japanese History II5 (4.0)
Extracurricular Activities
  • Japanese language and cultural studies as minor subject.
2015-2018
Warndtgymnasium
Higher Secondary School Certificate
GPA: 4.0
Awards:
  • School year's best student award
  • Computer Science award of Saarland University
  • Mathematics award of Saarland University
  • History award of Historic Society for the Saar-Region
2008-2015

Teaching Experience

Teaching Assistant

Oct 2019 - Present, School of Informatics, University of Edinburgh

Teaching assistant, demonstrator and marker for three iterations of the Reinforcement Learning lecture at the University of Einburgh under Dr. Stefano V. Albrecht

  • Holding lectures on implementation of RL systems and Deep RL
  • Designing RL project covering wide range of topics including dynamic programming, single- and multi-agent RL as well as deep RL
  • Marking project and exam for reinforcement learning course
  • Advising students on various challenges regarding lecture material and content

M.Sc. Student Supervision

Feb 2021 - Aug 2021, School of Informatics, University of Edinburgh

Co-supervised final Masters students’ projects at the University of Einburgh

  • Co-supervised two M.Sc. students through project proposal, refinement and execution towards final thesis
  • Assisted M.Sc. student from their thesis towards a successful workshop publication at NeurIPS 2021, and a successful main conference publication at NeurIPS 2022.

Lecturer and Coach

Sep 2017 - Oct 2017, Mathematics Preparation Course, Saarland University

Voluntary lecturer and coach for the mathematics preparation course preparing upcoming computer science undergraduate students for their studies

  • Assisted the organisation of the mathematics preparation course for upcoming computer science students aiming to introduce them to foundational mathematical concepts, the university and student life as a whole
  • Introduced ∼250 participants to the importance of mathematics for computer science, formal languages and predicate logic in daily lectures of the first week
  • Supervised two groups to provide feedback and further assistance in daily coaching-sessions
  • The course received the BESTE-award for special student commitment 2017 at Saarland University

Teaching Assistant

Oct 2016 - Mar 2017, Dependable Systems and Software Chair, Saarland University

Tutor for the Programming 1 lecture about functional programming at the Dependable Systems and Software Group chair of Saarland University under Prof. Dr. Holger Hermanns

  • Taught first-year students fundamental concepts of functional programming, basic complexity theory and inductive correctness proofs in weekly tutorials and office hours
  • Corrected weekly tests as well as mid- and endterm exams
  • Collectively created learning materials and discussed student progress as part of the whole teaching team

Reviewing

Conferences
NeurIPS 2022, NeurIPS 2021 and 2022 Datasets and Benchmark Track, ICML 2022 (top 10% outstanding reviewer award), AAMAS 2022
Workshops
Pre-registration experiment workshop at NeurIPS 2020

Skills

Recent Posts