👀

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/s4158… - huge congrats to everyone who made this happen, I couldn't be more proud 🥳

My colleague Martin recorded an awesome tutorial video of the WHAM Demonstrator - a tool that allows you to explore the capabilities of World and Human Action Models like Muse microsoft.com/en-us/research…

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: ted.com/talks/katja_ho…

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: msft.it/6012qahc2

Looking forward to presenting our study on representation learning for on-policy actor-critic algorithms in Singapore for #ICLR2025 ! Here's a picture to tease 3 key insights in our study... 1⃣ Decoupled actor-critic model architectures outperform their shared counterparts.

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

I'm excited to chat at #RLDM2025 about our (with Samuel Garcin) recent project: PixelBrax, where we combine the Brax physics engine with JAX-based rendering to enable end-to-end GPU training from pixels. paper: arxiv.org/abs/2502.00021 code: github.com/trevormcinroe/… Thread 1/

The Multi-Agent RL book has completely sold out! 😀 Reprints are now in production by The MIT Press @mitpress.bsky.social. We have updated the book with some corrections. The book PDF + errata, slides, code and exercises are available at marl-book.com.

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 😊

The Edinburgh RL reading group is back with regular meetings and a new website! Anyone is welcome to attend 👏

My Lab at the University of Edinburgh🇬🇧 has funded PhD positions for this cycle! We study the computational principles of how people learn, reason, and communicate. It's a new lab, and you will be playing a big role in shaping its culture and foundations. Spread the words!

It was great to visit The University of Sheffield 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!