This looks awesome! We need benchmarks that consider coordination between agents. Also super cool to see cross comparison between LLM/ VLM and MARL agents! Congrats to @kale-ab.bsky.social & co. 👏

Kale-ab Tessera@kale-ab.bsky.social · 3w ago

Can LLM agents coordinate in long-horizon, open-ended worlds? We test 13 LLMs in Alem, a new benchmark. Most struggle, averaging ~6% normalised return. Yet on Hard, zero-shot Gemini 3.1 Pro matches the best MARL agent after 1B training steps. Our ablations show communication matters most. 🧵

I'm delighted to announce the release of OpenSpiel 2.0! ♟️🎲♦️🎉 Structured types for states, observations, and actions, standard trajectories (based on JSON), 19 new games, AlphaZero ported to JAX, Windows PyPI support, language model fine-tuning examples and an MCP server (demo below 🤩👇)! 🧵 1/N

Can LLM agents coordinate in long-horizon, open-ended worlds? We test 13 LLMs in Alem, a new benchmark. Most struggle, averaging ~6% normalised return. Yet on Hard, zero-shot Gemini 3.1 Pro matches the best MARL agent after 1B training steps. Our ablations show communication matters most. 🧵

Presenting this tomorrow at 14:00–15:45, LEARN 2 Session, Akamas Room. Ping me if you are around at AAMAS & want to chat! 👐 Slides: kaleabtessera.com/assets/slide...

Kale-ab Tessera@kale-ab.bsky.social · 2mo ago

As we build more cooperative multi-agent envs, we should ask: are we really testing the properties that make Dec-POMDPs hard, partial observability and decentralised coordination, or can agents succeed via shortcuts? 🤔 Our #AAMAS2026 Oral probes this question 🔎🧵

As we build more cooperative multi-agent envs, we should ask: are we really testing the properties that make Dec-POMDPs hard, partial observability and decentralised coordination, or can agents succeed via shortcuts? 🤔 Our #AAMAS2026 Oral probes this question 🔎🧵

Next week I will be at AAMAS looking in awe @kale-ab.bsky.social presenting as an oral our paper on probing actual reasoning capabilities in Cooperative Multi-Agent Reinforcement Learning. More than happy to chat about this project or research in general!

Reading group TOMORROW 3-4pm UK! Joe Marino (Google DeepMind) will present SIMA 2, a generalist embodied agent designed to operate across a wide range of 3D virtual worlds 🌎 Join here: edinburgh-rl.github.io/reading-group

Reading group TODAY 2pm BST! "Despite years of research in offline reinforcement learning, the field has failed to deliver major breakthroughs..." Matthew Jackson and Jarek Liesen (Oxford) will present Unifloral - unified implementations and evaluations for offline RL: arxiv.org/abs/2504.11453

First time in a Waymo. Honestly, a pretty surreal experience! Surprised by how smooth the ride was and how quickly I felt comfortable in the car 😮

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

Kale-ab Tessera@kale-ab.bsky.social · last yr.

📜🤖 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!

Reading group today at 2pm BST! We are starting our NeurIPS series with Sable and Oryx, sequence models for scalable multi-agent coordination from the RL Research Team at InstaDeep. 🚀 Papers: - Sable: bit.ly/3Lme7jH - Oryx: bit.ly/47GJb4T Meeting: - bit.ly/3JoEbtU

📢 RL reading group Thursday @ 16:00 BST 📢 Speaker: Alex Lewandowski Title: The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis 🌍 Details: edinburgh-rl.github.io/reading-group

None of our impactful papers have had an easy path through traditional venues. Most cited paper? Rejected four times. Most impactful paper? Poster at a conference. But none of it matters because arxiv makes everything work

Great first couple of days at DLI @deeplearningindaba.bsky.social in Kigali 🇷🇼, some highlights include amazing talks talks by @verenarieser.bsky.social and Max Welling, great pracs and tuts, and of course the opening party ( before the rain 😢) 🎉 #DLI2025

We’re excited to unveil the first #DLI2025 lineup of tutorials and practicals: ✨ Machine Learning Foundations ✨ Generative Models & LLMs for African languages All tutorial content will also be available online after the Indaba. Don’t miss out, subscribe here 👉 lnkd.in/eCgXRqsV

🇨🇦 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! 🎉

Kale-ab Tessera@kale-ab.bsky.social · last yr.

📜🤖 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!

We are thrilled to announce our next keynote speaker @wellingmax.bsky.social, Professor at the University of Amsterdam, Visiting Professor at Caltech and CTO & Co-Founder of CuspAI. Catch his talk “How AI could transform the sciences” on August 18 at 4:30 PM GMT+2. #DLI2025

RL reading group TODAY @ 15:00 BST 🔥 Speaker: Cam Allen (Postdoc, UC Berkeley) Title: The Agent Must Choose the Problem Model Details: edinburgh-rl.github.io/reading-group

Reading group is back for those interested in RL/MARL/agents/open-endedness and alike... First session today at 3pm BST, @mattieml.bsky.social is presenting the Simplifying TD learning/PQN paper. 🎉 Meeting link: bit.ly/4lfdaGR Sign up: bit.ly/40xNQDR

RL & Agents Reading Group@rl-agents-rg.bsky.social · last yr.

We are super excited to kick things off again with Mattie Fellows (Postdoc @ FLAIR in Oxford) today 15:00 BST! Paper: Simplifying Deep Temporal Difference Learning Check out our website for full info edinburgh-rl.github.io/reading-grou...

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 😊

📜🤖 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!

For many, the Indaba was their first exposure to ML/AI, and this helps give more people that opportunity. Please donate if you can: gofund.me/61b012e4

Deep Learning Indaba@deeplearningindaba.bsky.social · last yr.

🪘Our Crowdfunding Campaign is LIVE! 🪘 🚀Support Indaba 2025 Participant Grants! 👉https://gofund.me/61b012e4 We are launching a crowdfunding campaign to directly fund essential travel and participation grants for students and researchers for the upcoming Indaba in Kigali, Rwanda.

🪘The 2024 Impact Report is here! Our last Indaba’s theme, Xam Xamlé (Wolof for "To Gather Knowledge and Share It"), beautifully reflected our mission: Empowering and educating through African AI. Read our report 🔗https://deeplearningindaba.com/blog/2025/04/xam-xamle-our-latest-indaba-impact-report/

The RLDM workshop list is now up! Have a look: rldm.org/call-for-wor... More workshop details coming soon :) There were so many wonderful submissions---this was really tough for the committee. Huge thanks to all involved, and looking forward to seeing folks in Dublin

We recently asked the authors to do a talk on this - m.youtube.com/watch?v=Bmdn... . A lot of awesome gems (goal focused rl research, don't waste your time, etc) 🔥 Thanks for bringing this to my attention @brandonrohrer.com !

Adam White - Empirical Design in Reinforcement Learning

YouTube video by UoE Agents Group

m.youtube.com

Brandon Rohrer@brandonrohrer.com · 2y ago

Adding my love letter to arxiv.org/pdf/2304.01315 Empirical Design in Reinforcement Learning by Andrew Patterson, Samuel Neumann, Martha White, Adam White JMLR 25 (2024) 1-63 #ReinforcementLearning These aren’t the heroes we deserve, but they are the heroes we need.

Reminder of how common paper rejections are, even for people like @teorth.bsky.social 💡

📚🧵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 🧵👇

The Deep Learning Indaba has made significant progress over the last few years. This piece in @mittechreviewbr.bsky.social paints a great picture of the opportunities and tensions we face 🙏🏾. And Lots more work for us still 🚀🚀 www.technologyreview.com/2024/11/11/1...

What Africa needs to do to become a major AI player

Inadequate funding, infrastructure issues, and fights over regulation mean the sector's future remains uncertain.

technologyreview.com

Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread

RLDM will be held next year in Dublin! A reminder that the call for workshops is out: rldm.org/call-for-wor... The workshops are one of my favourite parts of the conference :) please get in touch if you have any questions!

RLDM@rldmdublin2025.bsky.social · 2y ago

Come join us at Trinity College Dublin for the 6th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2025) Abstract deadline January 15: rldm.org/submit