Mikayel Samvelyan (@_samvelyan) / X

Mikayel Samvelyan

850 posts

Mikayel Samvelyan

@_samvelyan

@GoogleDeepMind Autonomous Discovery and Self-Improvement. Ex @Meta (FAIR) | @UCL | @UniofOxford.

London, England

Joined January 2018

Pinned
Mikayel Samvelyan
@_samvelyan
Nov 11, 2025
I’m hiring a Student Researcher at @GoogleDeepMind. This research role centers on topics of open-ended self-improvement and discovery with LLM agents. 📍 Location: London 🗓️ Duration: 6 months, 100% 🚀 Start date: June or July 2026 Apply now using the links below👇
111K
Mikayel Samvelyan
@_samvelyan
Aug 10, 2024
every damn time
43K
Mikayel Samvelyan
@_samvelyan
Oct 14, 2024
Thrilled to share that I’ve joined @GoogleDeepMind as a Research Scientist in the Open-Endedness Team. Excited to continue working with my brilliant PhD advisor @_rockt and the incredible team, including @jparkerholder & @MichaelD1729 who have greatly shaped my research journey.
42K
Mikayel Samvelyan
@_samvelyan
Sep 7, 2020
Thrilled to announce that today I joined @FacebookAI Research (FAIR) London and will soon start my PhD at @UCL under the supervision of Tim Rocktäschel (@_rockt). Excited to start this new chapter in my life and help #RL agent decide, act, and reason with knowledge at @UCL_DARK
Mikayel Samvelyan
@_samvelyan
Mar 7, 2023
I’m excited to share our latest #ICLR2023 paper 🏎️ MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning 🏎 Paper: arxiv.org/abs/2303.03376 Website: maestro.samvelyan.com Highlights: 👇
00:00
80K
Mikayel Samvelyan
@_samvelyan
Feb 27, 2024
Introducing 🌈 Rainbow Teaming, a new method for generating diverse adversarial prompts for LLMs via LLMs It's a versatile tool 🛠️ for diagnosing model vulnerabilities across domains and creating data to enhance robustness & safety 🦺 Co-lead w/ @sharathraparthy & @_andreilupu
00:00
56K
Mikayel Samvelyan
@_samvelyan
Jan 25, 2024
Uncovering vulnerabilities in multi-agent systems with the power of Open-Endedness! Introducing MADRID: Multi-Agent Diagnostics for Robustness via Illuminated Diversity ⚽️ Paper: arxiv.org/abs/2401.13460 Site: sites.google.com/view/madrid-ma… Code: 🔜 Here's what it's all about: 🧵👇
34K
Mikayel Samvelyan
@_samvelyan
Nov 19, 2024
#PhDone I am happy to share that I successfully defended my PhD thesis yesterday! 🎓 This wraps up an amazing journey, and I’m beyond grateful to everyone who’s been there for me along the way.
12K
Mikayel Samvelyan
@_samvelyan
Apr 26, 2023
I will be at #ICLR2023✈️ next week presenting MAESTRO, an approach for training agents able to generalize to new environments 🌎 and co-players 🤖in multi-agent settings. Happy to chat about multi-agent RL, open-endedness, autocurricula, or literally anything other than LLMs 🤭
00:10
Mikayel Samvelyan
@_samvelyan
Mar 7, 2023
I’m excited to share our latest #ICLR2023 paper 🏎️ MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning 🏎 Paper: arxiv.org/abs/2303.03376 Website: maestro.samvelyan.com Highlights: 👇
38K
Mikayel Samvelyan
@_samvelyan
Jul 30, 2024
Excited to share that our 🌈 Rainbow Teaming method has been used to evaluate and enhance the adversarial robustness of Llama 3.1 models! Originally an exploratory project co-led with @_andreilupu and @sharathraparthy, it has contributed to the biggest release of the year!
25K
Mikayel Samvelyan
@_samvelyan
Jan 10, 2024
The surge in #OpenEndedness research on arXiv marks a burgeoning interest in the field! The ascent is largely propelled by the trailblazing contributions of visionaries like @kenneth0stanley, @jeffclune, and @joelbot3000, whose work continues to pave new pathways.
54K
Mikayel Samvelyan
@_samvelyan
Sep 29, 2021
Creating rich and complex environments for RL has never been easier! I'm excited to introduce MiniHack: A Sandbox for Open-Ended Reinforcement Learning Research. Code: github.com/facebookresear… Paper: arxiv.org/abs/2109.13202 Blogpost: ai.facebook.com/blog/minihack-…
GIF
Mikayel Samvelyan
@_samvelyan
Apr 20, 2022
Thanks to @Bam4d, we now have a MiniHack Level Editor inside a browser which allows to easily design custom MiniHack environments using a convenient drag-and-drop functionality. Check it out at minihack-editor.github.io
Mikayel Samvelyan
@_samvelyan
Feb 14, 2025
⚔️ MiniHack Updates! ⚔️ 1️⃣ MiniHack 1.0.0 is here! Following popular demand, it now supports the new Gymnasium API and is built on NLE 1.1.0. Huge thanks to @stephen_oman (maintainer of @NetHack_LE ) for his outstanding contribution! 🙌
GIF
5.1K