🔥Telegram İfşa

Excited to share our latest work on Sequential Monte Carlo Policy Optimisation (SPO)🔥— a scalable, search-based RL algorithm leveraging SMC as a policy improvement operator for both continuous and discrete environments! 📍 Catch us tomorrow at #NeurIPS2024 (poster #94776) from

If you are interested in scalable search based 🔎 policy improvement operators come chat with me at our poster on SPO tommorow!

Want to learn how to beat SOTA on 35 out of 47 offline MARL tasks? Join us at #NeurIPS2024 to discover our latest Offline MARL breakthroughs. 📍 Visit poster #97812 tomorrow at 4:30 p.m. PST to learn more!

🚨 New reinforcement learning algorithms 🚨 Excited to announce MaxInfoRL, a class of model-free RL algorithms that solves complex continuous control tasks (including vision-based!) by steering exploration towards informative transitions. Details in the thread 👇

A short list of tips for keeping a clean, organized ML codebase for new researchers: eugenevinitsky.com/posts/quick-so…

This is truly the last chance for students to apply for free attendance at this year's edition. Don't let this final opportunity slip away! Apply here: indabax.co.za/register/ #Indaba𝕏SA

The 2025 Deep Learning Indaba𝕏 South Africa saw students and researchers who are passionate about ML innovations coming together in South Africa, with our team taking part in the action across talks, lessons and a hackathon challenge that put participants ML skills to the ultimate test. 🧑‍🔬

🎓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

Up next in our Online Learnathon series: Reinforcement Learning in action! 🔥 📌 Session Title: Train an AI Agent to Play Snake using Policy-Based Reinforcement Learning — Part 2 📖 Speakers: Ruan de Kock , Sasha Abramowitz, Siddarth Singh, Arnol Fokamᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠᅠ , Refiloe , and Matthew

We are heading to NeurIPS Conference 2025! 🎉 Our Africa-based Reinforcement Learning team are making headlines with: 3️⃣ Accepted papers ✨ 1 Spotlight (top 3%) 🎤 And our first-ever Oral presentation at NeurIPS (top 0.3%)! 🧵⬇️

Thrilled to announce that Oryx, our best-in-class algorithm for offline multi-agent reinforcement learning (MARL), has been accepted at NeurIPS Conference 2025! 🎉 Hear directly from lead author Omayma Mahjoub👇

Ahead of NeurIPS 2025, we’re answering your top questions on Oryx, InstaDeep’s new algorithm for offline multi-agent reinforcement learning (MARL). 📚 Hear from lead author Claude Formanek about how Oryx selects actions 🤔