BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning to Interact in Real-World Multiagent Systems - Markus Wul
 fmeier\, DeepMind
DTSTART:20250306T110000Z
DTEND:20250306T120000Z
UID:TALK227764@talks.cam.ac.uk
CONTACT:Sally Matthews
DESCRIPTION:From autonomous robots to digital assistants\, the future of A
 I is inherently multiagent—where systems must learn\, adapt\, and strate
 gize in dynamic environments. How do robots collaborate and compete to out
 maneuver opponents in soccer and push the limits in quadrotor racing? How 
 can AI help millions of users find the best routes every day? This talk ex
 plores the role of reinforcement learning in such settings\, where coopera
 tion and competition shape intelligent behavior. We will dive into robotic
 s applications like bipedal robot soccer and quadrotor racing\, alongside 
 large-scale digital systems such as Google Maps. By highlighting key chall
 enges and breakthroughs\, we will uncover how multiagent systems are shapi
 ng the next generation of autonomy.\n\nBio:\nMarkus Wulfmeier is a researc
 her in machine learning and robotics at Google DeepMind with a focus on fu
 ndamental and applied research on reinforcement\, imitation\, and transfer
  learning. His work aims at efficiently scalable algorithms across a varie
 ty of real-world applications including robotics\, navigation\, and langua
 ge modelling. Markus was a postdoctoral research scientist at the Oxford R
 obotics Institute and a member of Oxford University’s New College where 
 he completed his PhD. Over the years\, he has held visiting scholar positi
 ons with UC Berkeley\, MIT\, and ETH. His work received best paper awards 
 including IROS and GVSETS and was covered in the press including 60 Minute
 s\, The Verge\, MIT News\, Wired\, BBC News\, New Scientist\, and Popular 
 Science.
LOCATION:Department of Computer Science and technology\, FW26
END:VEVENT
END:VCALENDAR