BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Reinforcement Learning and Learning-guided Search for Generalizabi
 lity for Multi-agent Mobility Systems - Cathy Wu\, MIT
DTSTART:20240718T153000Z
DTEND:20240718T163000Z
UID:TALK219112@talks.cam.ac.uk
CONTACT:Amanda Prorok
DESCRIPTION:Designing transportation systems is an extensive process\, inv
 olving constant iteration between specifying modeling assumptions and solv
 ing for system performance. However\, increasing system complexity pushes 
 classical solution paradigms to their limits\, thus inhibiting engineers f
 rom understanding and designing future transportation systems. This talk e
 xplores the generalizability of alternative data-driven solution paradigms
 ––that is\, how gracefully they cope with changes to modeling assumpti
 ons. The talk considers two such approaches: deep reinforcement learning (
 RL) and learning-guided search. Despite superior performance of deep RL in
  some problems\, experimental findings suggest that the methods are fragil
 e to problem variations and thus are presently not suitable for iterative 
 design. On the other hand\, new learning-guided search methods effectively
  accelerate state-of-the-art solvers by up to 2-7 times. Furthermore\, exp
 eriments demonstrate their generalizability across problem variations\, th
 ereby indicating promise for iterative design. Applications discussed incl
 ude mixed autonomy traffic\, traffic signal control\, vehicle routing prob
 lems\, multi-robot warehousing\, and integer linear programming.
LOCATION:Department of Computer Science and technology\, FW26
END:VEVENT
END:VCALENDAR