BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Safe reinforcement learning with provable convergence guarantees
DTSTART:20230717T150000
DTEND:20230717T170000
DTSTAMP:20260407T125721Z
UID:73d68dc1bf3d5d9ba3406ee3560ac311e38081402b024bcb953f098a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Tingting Ni\nEDIC candidacy exam\nExam president: Prof. Patric
 k Thiran\nThesis advisor: Prof. Maryam Kamgarpour\nCo-examiner: Prof. Nico
 las Boumal\n\nAbstract\ncoming soon\n\nBackground papers\n1. Polyak\, B. T
 . (1963). Gradient methods for the minimisation of functionals. USSR Compu
 tational Mathematics and Mathematical Physics\, 3(4)\, 864-878. https://ww
 w.sciencedirect.com/science/article/pii/0041555363903823\n\n2. Usmanova\, 
 A. Krause\, and M. Kamgarpour. Safe non-smooth black-box optimization with
  application to policy search. In Learning for Dynamics and Control\, page
 s 980–989. PMLR\, 2020. https://proceedings.mlr.press/v120/usmanova20a.h
 tml\n\n3. Agarwal\, A.\, Kakade\, S. M.\, Lee\, J. D.\, & Mahajan\, G. (20
 21). On the theory of policy gradient methods: Optimality\, approximation\
 , and distribution shift. The Journal of Machine Learning Research\, 22(1)
 \, 4431-4506. https://proceedings.mlr.press/v125/agarwal20a.html
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR