Our paper on #MARL evaluation is accepted to #NeurIPS2022 🚀 I am truly honored and proud to work with these awesome co-authors at InstaDeep from Northern (Tunisia 🇹🇳) and Southern #Africa (South Africa 🇿🇦) :Omayma Mahjoub,Ruan de Kock, Siddarth Singh, Roland Dubb Arnu Pretorius

Thank you FRANCE 24 Français for covering our AI researchers Rihab Gorsane and Omayma Mahjoub - the first Africa-based 🌍female-led team published NeurIPS Conference🥇We’re so proud of them!🔥

From Africa to the "World Cup of AI" = NeurIPS! decisiveagents.com/capetocarthage Thanks for a beautiful journey Rihab Gorsane, Omayma Mahjoub, Ruan de Kock, Siddarth Singh, Zohra Slim and Karim Beguir. ❤️ Thanks Sara Hooker Sanmi Koyejo, Shakir Mohamed for your voice 🙏 I hope it inspires many! 🌍

📽️The documentary #CapeToCarthage spotlights our #MultiAgentReinforcementLearning research team. To empower a new generation, we developed Mava, our open source library that helps researchers build their own MARL systems in #JAX🛠️ Check it out here: github.com/instadeepai/Ma…

If you're interested in multi-agent RL, check out Mava! We have some of the fastest #JAX implementations in town ☄️, written in a research friendly way to get you started with your own ideas quickly!🌼

Excited about Multi-Agent Reinforcement Learning? Explore Mava, our open-source MARL library. With its lightning-fast JAX implementation, Mava simplifies building MARL systems, empowering new research⚡️ Featured in #CapeToCarthage, Mava is helping realize MARL's exciting future🚀

This Friday (08 Mar), the MARL Research Team at InstaDeep will be presenting their work on Growing the MARL software ecosystem in JAX at 9 AM PST. Looking forward to seeing y’all there!

Title: Growing the MARL software ecosystem in #JAXSpeakers: MARL Research Team InstaDeep Wednesday, 20 March 2024, 16h00 (GMT +2) zoomto.me/FwF7KThis crew have been doing amazing work! Please share with anyone who may be interested.

What happens when trying to learn multi-agent coordination from a static dataset? Catastrophe, if you’re not careful! This is the topic of our latest work on ✨Coordination Failure in Offline Multi-Agent Reinforcement Learning ✨ Curious about this image? Read below 👇 [1/16]

🚨 Thrilled to share our #ICML2025 paper: "Sable: a Performant, Efficient and Scalable Sequence Model for MARL"! We introduce a new SOTA cooperative Multi-Agent Reinforcement Learning algorithm that delivers the advantages of centralised learning without its drawbacks. (1/N)

Omayma Mahjoub Sasha Wiem Khlifi Liam Clark Arnu Pretorius 🧑‍🔬 Omayma Mahjoub and Wiem Khlifi will be presenting Sable at #ICML2025. 🗓️Wednesday, 16 July, 4:30 PM PDT 📍West Exhibition Hall B2-B3, Poster Number W-820 #MARL #AI #ICML2025 (8/N)

🎓Huge congratulations to Omer Kamal Ali Ebead and Ayman Saeed, top achievers in AIMS South Africa’s 2024-2025 AI for Science Master’s stream! Africa’s future in AI is in great hands. #AIMSSouthAfrica #AIforScience #AcademicExcellence #STEMinAfrica

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