Lukas Schäfer

In short, our paper derives new theory that explains when and why PIDMs show promise, especially in the low-data regime where BC often fails, and validates this theory in small-scale and realistic experiments. Checkout the preprint for more details!

Super excited to be able to share more about this project! At MSR, we have looked into PIDMs as alternative architectures for imitation learning to understand when and why they offer promise!

Learn more at the blog post: msft.it/6047QMkd3
and the arXiv preprint: arxiv.org/abs/2601.21718

Cohere Labs - Lukas Schäfer, Postdoc Researcher, Microsoft Research Cohere Labs - Lukas Schäfer - Decision-Making in Modern Video Games: From Human Play to World Models

I'll be giving a talk at Cohere Labs about my research on decision making agents and world models at Microsoft Research!

📅 January 20th (Tomorrow!)
5pm GMT/ 6pm CET/ 9am PST
📍 Online (link below)

Everyone is welcome! Link via calendar invite and more details:
cohere.com/events/coher...

It’s a wrap for me. Thanks a lot to the organisers for putting #EurIPS together, it’s been a fantastic week and one of my favourite conference experiences. Looking forward to seeing how this experiment will continue!🤞

Research Intern - Machine Learning - People Centric AI | Microsoft Careers In collaboration with your mentor and a diverse team, contribute to solving an ambitious research challenge and translate your results into actionable insights that are relevant to potential applicati...

📣We're hiring new research interns for 2026 at MSR Cambridge! If you're interested in ML research (esp. generative AI and/ or decision making agents), please consider applying. It's a great collaborative environment with a very kind and capable team!

apply.careers.microsoft.com/careers/job/...

On Saturday (6th Dec), I'll be at the EurIPS workshop on Epistemic Intelligence in Machine Learning where I'll be presenting a poster on the same topic! If this sounds interesting to you, please pop by and let us know what you think!

Tmrw (Tue 2nd Dec, 13:50-14:10), I'll be giving a talk on this topic titled "Exploiting State and Action Uncertainty for Imitation Learning using Inverse Dynamics Models" at the Interactive Learning and Interventional Representations (ILIR) workshop of the ELLIS UnConference!

I'll also be presenting work from my postdoc at MSR Cambridge in collaboration with the Game Intelligence team and MSR NYC. In our work, we dug deeper into recent imitation learning algorithms to theoretically & empirically understand what makes them work. You can find me talking about this 👇

I'm in Copenhagen for #EurIPS this week, please reach out if you'd like to chat about decision-making research!

I'm also on the academic job market for assistant professorship positions in Europe - if you believe I could be a good fit, please reach out, I'd love to connect and chat over☕!

Thrilled to present HyperMARL at #NeurIPS2025 in San Diego next week! 🚀 (Amos will present at
@euripsconf.bsky.social too.)

TL;DR: Coupling obs and agent IDs can hurt performance in MARL. Agent-conditioned hypernets cleanly decouple grads and enable specialisation.

📜: arxiv.org/abs/2412.04233

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!

Fingers crossed it’ll actually live up to the hype accumulated over all these years 🙏

Thanks for sharing, hadn’t seen this before and definitely plan to catch up!

🇨🇦 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! 🎉

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!

Love these curated and shareable feeds on here. Such a good feature to give more control to the users and community to make the experience what they want it to be rather than leaving it in the control of the platform!

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! 👇

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...

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.

Thanks! @sharky6000.bsky.social

GitHub - marl-book/marl-book-exercises: Code exercises for the MARL Textbook Code exercises for the MARL Textbook. Contribute to marl-book/marl-book-exercises development by creating an account on GitHub.

We also updated and moved our code exercises which we had built for a summer school to the marl-book github page so they can be easily found at github.com/marl-book/ma...

Thanks @sacha2.bsky.social for the reminder on that! They had previously been hidden inside my GitHub account 😅

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

GitHub - LukasSchaefer/marl-book-exercises: Code exercises for the MARL Textbook Code exercises for the MARL Textbook. Contribute to LukasSchaefer/marl-book-exercises development by creating an account on GitHub.

Awesome to see the slides publicly available, wasn’t aware they are now!

And yes actually, the code exercises are here: github.com/LukasSchaefe...

Good point though, I wanted to migrate them to the book github project. I’ll have a stab at that later!

📜🤖 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!

Thanks, will check it out!

That sounds exciting! Are there any recordings or slides available to check this out? 👀

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

Thanks!

We wanted to have a game with more realistic visuals. We decided on CS:GO mainly since there already existed an open dataset to train on and compare results to prior methods that used the same dataset.

Also, we finished initial experiments actually on the same day as CS2 released 😅

Thanks for the encouragement Marc — I’ll look out for you!

Thank!