Lukas Schäfer
@lukaschaefer.bsky.social
www.lukaschaefer.com
Researcher @msftresearch.bsky.social; working on autonomous agents in video games; PhD Univ of Edinburgh ; Ex Huawei Noah’s Ark Lab, Dematic; Young researcher HLF 2022
Researcher @msftresearch.bsky.social; working on autonomous agents in video games; PhD Univ of Edinburgh ; Ex Huawei Noah’s Ark Lab, Dematic; Young researcher HLF 2022
Pinned
Lukas Schäfer
@lukaschaefer.bsky.social
· Jun 19
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
Our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” has sold out! Another print round with minor corrections is in production with @mitpress.bsky.social and coming 👏
An errata of these corrections and the updated book PDF can already be found at www.marl-book.com
An errata of these corrections and the updated book PDF can already be found at www.marl-book.com
It was great to visit @sheffielduni.bsky.social today to give an invited talk on work from my PostDoc at MSR, and have a chance to talk to students and faculty at the CS department. Thanks a lot to Robert Loftin for the kind invitation and for hosting me!
October 20, 2025 at 4:58 PM
It was great to visit @sheffielduni.bsky.social today to give an invited talk on work from my PostDoc at MSR, and have a chance to talk to students and faculty at the CS department. Thanks a lot to Robert Loftin for the kind invitation and for hosting me!
Reposted by Lukas Schäfer
🇨🇦 Heading to @rl-conference.bsky.social next week to present HyperMARL (@cocomarl-workshop.bsky.social) and Remember Markov (Finding The Frame Workshop).
If you are around, hmu, happy to chat about Multi-Agent Systems (MARL, agentic systems), open-endedness, environments, or anything related! 🎉
If you are around, hmu, happy to chat about Multi-Agent Systems (MARL, agentic systems), open-endedness, environments, or anything related! 🎉
August 3, 2025 at 10:41 AM
🇨🇦 Heading to @rl-conference.bsky.social next week to present HyperMARL (@cocomarl-workshop.bsky.social) and Remember Markov (Finding The Frame Workshop).
If you are around, hmu, happy to chat about Multi-Agent Systems (MARL, agentic systems), open-endedness, environments, or anything related! 🎉
If you are around, hmu, happy to chat about Multi-Agent Systems (MARL, agentic systems), open-endedness, environments, or anything related! 🎉
Reposted by Lukas Schäfer
Will be at ICML and looking to hire a postdoc to help us scale up and deploy RL in self-driving. So, hit me up to chat.
July 10, 2025 at 11:24 PM
Will be at ICML and looking to hire a postdoc to help us scale up and deploy RL in self-driving. So, hit me up to chat.
The Edinburgh RL Reading group is back with a fresh new website 👏
Anyone is welcome to attend!
Anyone is welcome to attend!
Hello world! This is the RL & Agents Reading Group
We organise regular meetings to discuss recent papers in Reinforcement Learning (RL), Multi-Agent RL and related areas (open-ended learning, LLM agents, robotics, etc).
Meetings take place online and are open to everyone 😊
We organise regular meetings to discuss recent papers in Reinforcement Learning (RL), Multi-Agent RL and related areas (open-ended learning, LLM agents, robotics, etc).
Meetings take place online and are open to everyone 😊
July 10, 2025 at 11:10 AM
The Edinburgh RL Reading group is back with a fresh new website 👏
Anyone is welcome to attend!
Anyone is welcome to attend!
Eugene is awesome! — if you are interested in autonomous driving and RL, and New York sounds like an exciting place for a postdoc then this is an amazing opportunity! 👇
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Robust Autonomy Emerges from Self-Play
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...
arxiv.org
June 23, 2025 at 9:10 AM
Eugene is awesome! — if you are interested in autonomous driving and RL, and New York sounds like an exciting place for a postdoc then this is an amazing opportunity! 👇
Reposted by Lukas Schäfer
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Robust Autonomy Emerges from Self-Play
Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic drivi...
arxiv.org
June 21, 2025 at 5:14 PM
Hiring a postdoc to scale up and deploy RL-based planning onto some self-driving cars! We'll be building on arxiv.org/abs/2502.03349 and learn what the limits and challenges of RL planning are. Shoot me a message if interested and help spread the word please!
Full posting to come in a bit.
Full posting to come in a bit.
Our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” has sold out! Another print round with minor corrections is in production with @mitpress.bsky.social and coming 👏
An errata of these corrections and the updated book PDF can already be found at www.marl-book.com
An errata of these corrections and the updated book PDF can already be found at www.marl-book.com
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
June 19, 2025 at 8:26 AM
Our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” has sold out! Another print round with minor corrections is in production with @mitpress.bsky.social and coming 👏
An errata of these corrections and the updated book PDF can already be found at www.marl-book.com
An errata of these corrections and the updated book PDF can already be found at www.marl-book.com
Reposted by Lukas Schäfer
📜🤖 Can a shared multi-agent RL policy support both specialised & homogeneous team behaviours -- without changing the learning objective, requiring preset diversity levels or sequential updates? Our preprint “𝘏𝘺𝘱𝘦𝘳𝘔𝘈𝘙𝘓: 𝘈𝘥𝘢𝘱𝘵𝘪𝘷𝘦 𝘏𝘺𝘱𝘦𝘳𝘯𝘦𝘵𝘸𝘰𝘳𝘬𝘴 𝘧𝘰𝘳 𝘔𝘶𝘭𝘵𝘪-𝘈𝘨𝘦𝘯𝘵 𝘙𝘓” explores this!
May 27, 2025 at 11:07 AM
📜🤖 Can a shared multi-agent RL policy support both specialised & homogeneous team behaviours -- without changing the learning objective, requiring preset diversity levels or sequential updates? Our preprint “𝘏𝘺𝘱𝘦𝘳𝘔𝘈𝘙𝘓: 𝘈𝘥𝘢𝘱𝘵𝘪𝘷𝘦 𝘏𝘺𝘱𝘦𝘳𝘯𝘦𝘵𝘸𝘰𝘳𝘬𝘴 𝘧𝘰𝘳 𝘔𝘶𝘭𝘵𝘪-𝘈𝘨𝘦𝘯𝘵 𝘙𝘓” explores this!
Today, I’ll be presenting our work on exploration in MARL using ensembles here! 👇
Multiagent Learning Session
Where: Ambassador Ballroom 1 & 2
When: 14:00 - 14:13
I’ll also present the poster later at the Learn track of the poster session at 15:45 - 16:30
Multiagent Learning Session
Where: Ambassador Ballroom 1 & 2
When: 14:00 - 14:13
I’ll also present the poster later at the Learn track of the poster session at 15:45 - 16:30
At the main conference, I'll be presenting our work on using ensembles of value functions for multi-agent exploration!
I'll be presenting the oral at the Multi-agent Learning 1 session on Wednesday (2:00 - 3:45pm), and the poster after 3:45pm!
Paper: arxiv.org/abs/2302.03439
I'll be presenting the oral at the Multi-agent Learning 1 session on Wednesday (2:00 - 3:45pm), and the poster after 3:45pm!
Paper: arxiv.org/abs/2302.03439
May 21, 2025 at 3:18 PM
Today, I’ll be presenting our work on exploration in MARL using ensembles here! 👇
Multiagent Learning Session
Where: Ambassador Ballroom 1 & 2
When: 14:00 - 14:13
I’ll also present the poster later at the Learn track of the poster session at 15:45 - 16:30
Multiagent Learning Session
Where: Ambassador Ballroom 1 & 2
When: 14:00 - 14:13
I’ll also present the poster later at the Learn track of the poster session at 15:45 - 16:30
On my way to Detroit for @aamasconf.bsky.social! Looking forward to presenting the last work from my PhD at the main conference, and work from @msftresearch.bsky.social at the Adaptive and Learning Agents Workshop. More info 👇
If you'd like to chat, feel free to DM me!
If you'd like to chat, feel free to DM me!
May 18, 2025 at 9:40 AM
On my way to Detroit for @aamasconf.bsky.social! Looking forward to presenting the last work from my PhD at the main conference, and work from @msftresearch.bsky.social at the Adaptive and Learning Agents Workshop. More info 👇
If you'd like to chat, feel free to DM me!
If you'd like to chat, feel free to DM me!
Reposted by Lukas Schäfer
We are making available an experimental and interactive real-time gameplay experience in Copilot Labs, powered by our Muse family of world models. Learn more about the research underpinning this experience: www.microsoft.com/en-us/resear...
WHAMM! Real-time world modelling of interactive environments. - Microsoft Research
Today we are making available an interactive real-time gameplay experience in Copilot Labs, powered by our Muse family of world models. This blog post provides a deeper look at the research underpinni...
www.microsoft.com
April 7, 2025 at 7:08 PM
We are making available an experimental and interactive real-time gameplay experience in Copilot Labs, powered by our Muse family of world models. Learn more about the research underpinning this experience: www.microsoft.com/en-us/resear...
Reposted by Lukas Schäfer
Call for papers! 🎉 If you have felt confused about evaluation in explainable AI, this workshop is for you! We are excited to go to Bologna @ ECAI'25 as we try to build better methods for evaluating XAI. Can't wait to see what ideas the community will bring!
sites.google.com/view/excd-20...
sites.google.com/view/excd-20...
March 14, 2025 at 3:41 PM
Call for papers! 🎉 If you have felt confused about evaluation in explainable AI, this workshop is for you! We are excited to go to Bologna @ ECAI'25 as we try to build better methods for evaluating XAI. Can't wait to see what ideas the community will bring!
sites.google.com/view/excd-20...
sites.google.com/view/excd-20...
Reposted by Lukas Schäfer
My group @FLAIR_Ox is recruiting a postdoc and looking for someone who can get started by the end of April. Deadline to apply is in one week (!), 19th of March at noon, so please help spread the word: my.corehr.com/pls/uoxrecru...
Job Details
my.corehr.com
March 12, 2025 at 3:17 PM
My group @FLAIR_Ox is recruiting a postdoc and looking for someone who can get started by the end of April. Deadline to apply is in one week (!), 19th of March at noon, so please help spread the word: my.corehr.com/pls/uoxrecru...
Reposted by Lukas Schäfer
What happens when we train generative AI models to predict everything that happens in a modern video game? In my TED AI talk I share insights from how AI can learn the physics of a game, and how this research could empower game creatives: www.ted.com/talks/katja_...
Why we're training AI on video games
AI is already a powerful tool for collaboration — but this is just the tip of the iceberg, says AI researcher Katja Hofmann. She describes her team's work training AI on years of human gameplay data f...
www.ted.com
March 7, 2025 at 6:00 PM
What happens when we train generative AI models to predict everything that happens in a modern video game? In my TED AI talk I share insights from how AI can learn the physics of a game, and how this research could empower game creatives: www.ted.com/talks/katja_...
Reposted by Lukas Schäfer
Today in Nature: our research on world and human action models (WHAM) - generative ai models of video games, aimed towards supporting game creatives in gameplay ideation : nature.com/articles/s41... - huge congrats to everyone who made this happen, I couldn't be more proud 🥳
World and Human Action Models towards gameplay ideation - Nature
A state-of-the-art generative artificial intelligence model of a video game is introduced to allow the support of human creative ideation, with the analysis of user study data highlighting three neces...
nature.com
February 19, 2025 at 5:55 PM
Today in Nature: our research on world and human action models (WHAM) - generative ai models of video games, aimed towards supporting game creatives in gameplay ideation : nature.com/articles/s41... - huge congrats to everyone who made this happen, I couldn't be more proud 🥳
Awesome to see this released and out in the world now. Huge congrats to the entire team!
It was super cool to see the vision come to life as an intern and everything coming together now after re-joining the team 👏
It was super cool to see the vision come to life as an intern and everything coming together now after re-joining the team 👏
Nature published Microsoft research detailing our WHAM, an AI model that generates video game visuals & controller actions. We're releasing the model weights, sample data & WHAM Demonstrator on Azure AI Foundry to enable researchers to build on this work. www.microsoft.com/en-us/resear...
February 19, 2025 at 4:41 PM
Awesome to see this released and out in the world now. Huge congrats to the entire team!
It was super cool to see the vision come to life as an intern and everything coming together now after re-joining the team 👏
It was super cool to see the vision come to life as an intern and everything coming together now after re-joining the team 👏
Reposted by Lukas Schäfer
An exciting new internship opportunity in my team: Generative AI for Human Creativity - in the context of a multi-disciplinary internship with a fantastic set of mentors 🤩
Search Jobs | Microsoft Careers
jobs.careers.microsoft.com
January 13, 2025 at 1:06 PM
An exciting new internship opportunity in my team: Generative AI for Human Creativity - in the context of a multi-disciplinary internship with a fantastic set of mentors 🤩
I had an awesome experience at the AAMAS doctoral consortium (despite virtual format) and would highly recommend it to any PhD student.
@sharky6000.bsky.social has been an amazing mentor who gave me lots of motivation and advice for my journey forward!
Deadline in 7 days so apply soon 👇
@sharky6000.bsky.social has been an amazing mentor who gave me lots of motivation and advice for my journey forward!
Deadline in 7 days so apply soon 👇
As a PhD student, would you like the opportunity to interact closely with established researchers and other students, receive feedback on your work, and get advice on managing your career?
Check out the Doctoral Consortium at #AAMAS 2025! Deadline: Jan 17th.
aamas2025.org/index.php/co...
Check out the Doctoral Consortium at #AAMAS 2025! Deadline: Jan 17th.
aamas2025.org/index.php/co...
Call for Contributions to the Doctoral Consortium – AAMAS 2025 Detroit
aamas2025.org
January 10, 2025 at 5:05 PM
I had an awesome experience at the AAMAS doctoral consortium (despite virtual format) and would highly recommend it to any PhD student.
@sharky6000.bsky.social has been an amazing mentor who gave me lots of motivation and advice for my journey forward!
Deadline in 7 days so apply soon 👇
@sharky6000.bsky.social has been an amazing mentor who gave me lots of motivation and advice for my journey forward!
Deadline in 7 days so apply soon 👇
Reposted by Lukas Schäfer
The first textbook on multi-agent reinforcement learning is out - a landmark for the field, the first textbook covering game-theoretic foundations with state-of-the-art deep learning! Congrats to its authors Stefano Albrecht , LukasSchaefer and Filippos Christianos
More details: www.marl-book.com
More details: www.marl-book.com
Multi-Agent Reinforcement Learning: Foundations and Modern Approaches
Textbook published by MIT Press (2024)
www.marl-book.com
December 18, 2024 at 6:05 PM
The first textbook on multi-agent reinforcement learning is out - a landmark for the field, the first textbook covering game-theoretic foundations with state-of-the-art deep learning! Congrats to its authors Stefano Albrecht , LukasSchaefer and Filippos Christianos
More details: www.marl-book.com
More details: www.marl-book.com
📚📢Christmas came early 🎅
Our new textbook on multi-agent reinforcement learning with @mitpress.bsky.social is out NOW!
The book is available from MIT Press (mitpress.mit.edu/978026204937...) or your bookstore nearby.
Why you should be interested, what you get, and more all in a 🧵👇
Our new textbook on multi-agent reinforcement learning with @mitpress.bsky.social is out NOW!
The book is available from MIT Press (mitpress.mit.edu/978026204937...) or your bookstore nearby.
Why you should be interested, what you get, and more all in a 🧵👇
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
December 17, 2024 at 2:32 PM
📚📢Christmas came early 🎅
Our new textbook on multi-agent reinforcement learning with @mitpress.bsky.social is out NOW!
The book is available from MIT Press (mitpress.mit.edu/978026204937...) or your bookstore nearby.
Why you should be interested, what you get, and more all in a 🧵👇
Our new textbook on multi-agent reinforcement learning with @mitpress.bsky.social is out NOW!
The book is available from MIT Press (mitpress.mit.edu/978026204937...) or your bookstore nearby.
Why you should be interested, what you get, and more all in a 🧵👇
Reposted by Lukas Schäfer
My team at Waymo is hiring two London-based interns for Summer 2025. Please consider applying!
careers.withwaymo.com/jobs/2025-su...
careers.withwaymo.com/jobs/2025-su...
careers.withwaymo.com/jobs/2025-su...
careers.withwaymo.com/jobs/2025-su...
2025 Summer Intern, MS/PhD, Research - Simulation Agents - London, England, United Kingdom
Waymo is an autonomous driving technology company with the mission to be the most trusted driver. Since its start as the Google Self-Driving Car Project in 2009, Waymo has focused on building the Waym...
careers.withwaymo.com
December 13, 2024 at 7:37 AM
My team at Waymo is hiring two London-based interns for Summer 2025. Please consider applying!
careers.withwaymo.com/jobs/2025-su...
careers.withwaymo.com/jobs/2025-su...
careers.withwaymo.com/jobs/2025-su...
careers.withwaymo.com/jobs/2025-su...
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
December 9, 2024 at 6:34 PM
📚🧵1/7 It is finally here!! Only one more week until the print release of our textbook “Multi-Agent Reinforcement Learning: Foundations and Modern Approaches” with @mitpress.bsky.social!
What you get, why you should be interested and more, all below in a short 🧵👇
What you get, why you should be interested and more, all below in a short 🧵👇
Excellent points being made and I’m sure everyone can resonate with this experience.
Let’s try to be the reviewer we’d like to have and improve the work we review rather than being antagonistic and trying to find reasons to reject.
Let’s try to be the reviewer we’d like to have and improve the work we review rather than being antagonistic and trying to find reasons to reject.
To paraphrase Dennett (rip 💔), the goal of reviewing is to determine truth, not to conquer your opponent.
Too many reviewers seem to not have internalised this. In my opinion, this is the hardest lesson a reviewer has to learn, and I want to share some thoughts.
Too many reviewers seem to not have internalised this. In my opinion, this is the hardest lesson a reviewer has to learn, and I want to share some thoughts.
November 27, 2024 at 6:22 PM
Excellent points being made and I’m sure everyone can resonate with this experience.
Let’s try to be the reviewer we’d like to have and improve the work we review rather than being antagonistic and trying to find reasons to reject.
Let’s try to be the reviewer we’d like to have and improve the work we review rather than being antagonistic and trying to find reasons to reject.
Reposted by Lukas Schäfer
To paraphrase Dennett (rip 💔), the goal of reviewing is to determine truth, not to conquer your opponent.
Too many reviewers seem to not have internalised this. In my opinion, this is the hardest lesson a reviewer has to learn, and I want to share some thoughts.
Too many reviewers seem to not have internalised this. In my opinion, this is the hardest lesson a reviewer has to learn, and I want to share some thoughts.
November 27, 2024 at 5:25 PM
To paraphrase Dennett (rip 💔), the goal of reviewing is to determine truth, not to conquer your opponent.
Too many reviewers seem to not have internalised this. In my opinion, this is the hardest lesson a reviewer has to learn, and I want to share some thoughts.
Too many reviewers seem to not have internalised this. In my opinion, this is the hardest lesson a reviewer has to learn, and I want to share some thoughts.
Reposted by Lukas Schäfer
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
November 26, 2024 at 6:15 AM
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/
fleuret.org/dlc/
And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)
fleuret.org/lbdl/