BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Understanding Feature Dynamics in Policy Optimization
DTSTART:20231027T100000
DTEND:20231027T120000
DTSTAMP:20260407T111335Z
UID:b3c36af9cacc9e05b3673f93954fa1245ddd67c06c664496bf507a6b
CATEGORIES:Conferences - Seminars
DESCRIPTION:Skander Moalla\nEDIC candidacy exam\nExam president: Prof. Vol
 kan Cevher\nThesis advisor: Prof. Caglar Gulcehre\nCo-examiner: Prof. Alex
 andre Alahi\n\nAbstract\ncoming soon\n\nBackground papers\n- Proximal Poli
 cy Optimization Algorithms (Schulman et al. 2017) <https://arxiv.org/abs/1
 707.06347> \n- Transient Non-stationarity and Generalisation in Deep Rein
 forcement Learning (Igl et al. 2020) <https://openreview.net/forum?id=Qun8
 fv4qSby>\n- Understanding and Preventing Capacity Loss in Reinforcement Le
 arning (Lyle et al. 2022) <https://openreview.net/forum?id=ZkC8wKoLbQ7>\n
  
LOCATION:BC 233 https://plan.epfl.ch/?room==BC%20233
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR