/Tech3h ago

Multi-Agent RL Project Advances Quadrotor Racing Sim-To-Real Transfer

1421780

Original post

Great summery of our multi-agent quadrotor racing project in @jackclarkSF's ImportAI newsletter [1]!

While a massive success for racing, the project opened more questions than it answered, going far beyond technical aspects.

For now, additional technical bits: Multiagent learning really became key for us to transfer from simulation to human behaviours. It directly mirrors the role of targeted domain randomisation for transferring to new visual or dynamic aspects #sim2real

The perceiver choice actually nicely reflects recent successes for offline RL from previous colleagues @GoogleDeepMind [2]

8:09 AM · Jun 14, 2026 · 466 Views

Sentiment

Sentiment building, check back later.

Cluster Engagement

Posts from X

Most Activity

Markus Wulfmeier@m_wulfmeier

[1] https://importai.substack.com/p/import-ai-460-reward-hacking-society

[2] https://sites.google.com/view/perceiver-actor-critic

Markus Wulfmeier@m_wulfmeier

Great summery of our multi-agent quadrotor racing project in @jackclarkSF's ImportAI newsletter [1]!

While a massive success for racing, the project opened more questions than it answered, going far beyond technical aspects.

The perceiver choice actually nicely reflects recent successes for offline RL from previous colleagues @GoogleDeepMind [2]

3h31400