Ruan de Kock

70 posts

Ruan de Kock banner
Ruan de Kock

Ruan de Kock

@ruanjohn

Research engineer @instadeepai focusing on multi-agent systems 🤖

Katılım Kasım 2010
303 Takip Edilen141 Takipçiler
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
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. 👇
English
1
3
4
212
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
🧩 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.
English
1
5
7
256
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
🚀 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. 🧵⬇️
English
1
11
17
1.5K
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
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 🤔
English
1
3
9
345
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
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👇
English
1
7
14
439
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
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%)! 🧵⬇️
InstaDeep tweet media
English
1
5
8
909
Ruan de Kock retweetledi
Deep Learning Indaba
Deep Learning Indaba@DeepIndaba·
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 Morris 🕘 Time: Saturday, 13 September | 11 am – 1 pm (UTC+2), add to calendar 👉 shorturl.at/Qapjl In this hands-on practical, we’ll tackle the limitations of the REINFORCE algorithm and introduce value functions as a solution. Participants will learn to implement the A2C (Advantage Actor-Critic) algorithm, building on the previous session’s codebase, and train an agent to play Snake. By the end, you’ll understand why A2C improves over REINFORCE and gain practical skills to apply it to real reinforcement learning problems. ✨ Don’t miss this chance to level up your RL knowledge with expert guidance!
Deep Learning Indaba tweet media
English
0
12
36
2.1K
Elon Musk
Elon Musk@elonmusk·
This false nomenclature of “researcher” and “engineer”, which is a thinly-masked way of describing a two-tier engineering system, is being deleted from @xAI today. There are only engineers. Researcher is a relic term from academia.
Aditya Gupta@adityagupta

we at @xai are looking for researchers and engineers for scaling up our rl environments with user feedback and preference in the loop. apply here (or drop me a dm): x.com/i/jobs/1948556…

English
7.7K
6.3K
52.2K
32.2M
Ruan de Kock retweetledi
InstaDeep
InstaDeep@instadeepai·
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. 🧑‍🔬
InstaDeep tweet mediaInstaDeep tweet mediaInstaDeep tweet mediaInstaDeep tweet media
English
1
4
14
764
Ruan de Kock
Ruan de Kock@ruanjohn·
🚨 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)
Ruan de Kock tweet media
English
2
10
30
2.5K
Ruan de Kock retweetledi