BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261017T232916EDT-43300ML7Uf@132.216.98.100
DTSTAMP:20261018T032916Z
DESCRIPTION:ISS Informal Systems Seminar\n\nSpeaker: Pierre-Luc Bacon – Uni
 versité de Montréal\, Canada \n\n \n\n\n\nPresentation on YouTube\n\nAbstr
 act: Decision awareness is the learning principle according to which the c
 omponents of a learning system ought to be optimized directly to satisfy t
 he global performance criterion: to produce optimal decisions. This end-to
 -end perspective has recently led to significant advances in model-based r
 einforcement learning by addressing the problem of compounding errors plag
 uing alternative approaches. In this talk\, I will present some of our rec
 ent work on this topic: 1. on learning control-oriented transition models 
 by implicit differentiation and 2. on learning neural ordinary differentia
 l equations end-to-end for nonlinear trajectory optimization. Along the wa
 y\, we will also discuss some of the computational challenges associated w
 ith those methods and our attempts at scaling up performance\, specificall
 y: using an efficient factorization of the Jacobians in the forward mode o
 f automatic differentiation through novel constrained optimizers inspired 
 by adversarial learning.\n\n\nBiography: Pierre-Luc Bacon is an assistant 
 professor at the University of Montreal in the Computer Science and Operat
 ions Research department. He is also a core member of Mila and Ivado and a
  Facebook CIFAR chair holder. He leads a research group of 15 students wor
 king on the challenge posed by the curse of the horizon in reinforcement l
 earning and optimal control.\n
DTSTART:20230210T170000Z
DTEND:20230210T180000Z
LOCATION:CA\, ZOOM
SUMMARY:Decision Awareness in Reinforcement Learning 
URL:https://www.mcgill.ca/cim/channels/event/decision-awareness-reinforceme
 nt-learning-351638
END:VEVENT
END:VCALENDAR