Ruan de Kock
@ruanjohn
Followers
145
Following
334
Media
3
Statuses
70
Research Engineer @instadeepai focusing on Multi-agent RL 🤖
Cape Town, South Africa
Joined November 2010
Daniel is an exceptional talent! Have a look at his story.
We're extremely proud to share Daniel's achievement as part of our first oral presentation at @NeurIPSConf, representing an opportunity for AI researchers in Madagascar and across Africa to push new boundaries on the world stage. 🗺️
0
0
0
This year's @NeurIPSConf is nearly here, and we’re thrilled to be contributing to this year’s lineup with our Spotlight paper on MEMENTO. Lead author @RefiloeShabe explains how incorporating memory can help tackle more challenging routing problems, below. 👇
1
3
4
🧩 Proud to share that our research introducing MEMENTO, a memory-enhanced framework for neural combinatorial optimisation, has been selected as a Spotlight paper at @NeurIPSConf 2025! 🎉 👇 Hear from lead author, @ChalumeauFelix in the video below.
1
5
8
🚀 Proud to share that our research showing how inference-time strategies can break the reinforcement learning performance ceiling has been selected for an oral presentation at @NeurIPSConf 2025! 🎉 👇 Hear from lead authors @ChalumeauFelix and @ruanjohn in the ▶️ below. 🧵⬇️
1
11
16
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 🤔
1
3
9
Thrilled to announce that Oryx, our best-in-class algorithm for offline multi-agent reinforcement learning (MARL), has been accepted at @NeurIPSConf 2025! 🎉 Hear directly from lead author @MahjoubOmayma👇
1
7
14
We are heading to @NeurIPSConf 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%)! 🧵⬇️
1
5
8
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: @ruanjohn , Sasha Abramowitz, Siddarth Singh, @ArnolFokam , @RefiloeShabe , and Matthew
0
12
36
🎓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
1
4
16
The 2025 @DeepIndabaX_ZA 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. 🧑🔬
1
4
14
@MahjoubOmayma @sMashaZa @khlifi_wiem @liamclarkza @ArnuPretorius 🧑🔬 @MahjoubOmayma and @khlifi_wiem 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)
0
1
7
@MahjoubOmayma @sMashaZa @khlifi_wiem @liamclarkza @ArnuPretorius If you are interested, have a look at the full paper and code: 📜Paper: https://t.co/kSXjAF3CmD 🧑💻Code: https://t.co/rX1V6UB68W 🌐Website/Data: https://t.co/fIozA32XjH (7/N)
1
0
6
🎉 A massive thank you to my incredible co-authors @MahjoubOmayma @sMashaZa @khlifi_wiem Simon du Toit, Jemma Daniel, Louay Ben Nessir, Louise Beyers, Claude Formanek, @liamclarkza & @ArnuPretorius (6/N)
1
0
5
⚡Despite its power, Sable is remarkably efficient. It scales to over 1000 agents with linear memory increase and boasts 7x better GPU memory efficiency and up to a 6.5x improvement in throughput compared to MAT (previous SOTA). (5/N)
1
0
5
🔬In a benchmark across 45 diverse tasks (the largest in the literature), Sable substantially outperformed existing methods, ranking best 11 times more often than previous SOTA methods. (4/N)
1
0
5
💪 Our solution? Sable adapts the retention mechanism from Retentive Networks (RetNets) and achieves centralised learning advantages without the associated drawbacks. This allows for efficient, long-term memory and impressive scalability. (3/N)
1
0
5
🤔 The challenge? Centralised training in MARL performs well but cannot scale, limiting its use to scenarios with only a few agents. This creates a trade-off between performance and agent scalability. (2/N)
1
0
4
🚨 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)
2
10
30
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: https://t.co/y9fJOh9MzP
#Indaba𝕏SA
You asked, we listened! Indaba𝕏🇿🇦'25 Student Application Deadline Extended! Thank you for your interest & feedback! We've received requests to extend the application window, we're happy to announce that applications have been extended to Sunday, May 25th. https://t.co/y9fJOh9MzP
0
2
3
🚨 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 👇
8
95
592