BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.3.5//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:589@cran.univ-lorraine.fr
DTSTART;TZID=Europe/Paris:20241213T140000
DTEND;TZID=Europe/Paris:20241213T170000
DTSTAMP:20241112T074742Z
URL:https://www.cran.univ-lorraine.fr/events/soutenance-de-these-soha-kans
 o/
SUMMARY:Soutenance de thèse Soha KANSO
DESCRIPTION:Titre: Contributions to Safe Reinforcement Learning and Degrada
 tion Tolerant Control Design\n\nRésumé:This thesis develops an off-polic
 y safe Reinforcement Learning (RL) approach for the regulation and the tra
 cking problem in continuous-time nonlinear systems affine in control input
 . A novel approach is proposed that ensures system stability and safety du
 ring all phases: initialization\, exploration\, and exploitation. By using
  quadratic programming with control Lyapunov function (CLF) and control ba
 rrier function (CBF)\, the proposed approach ensures stability and safety 
 of the system during initialization and exploration phases. Furthermore\, 
 during exploitation\, the safety of the learned policy is ensured by augme
 nting the cost function with reciprocal CBFs\, thus balancing performance 
 optimization and safety. Moreover\, this thesis focuses on addressing actu
 ator degradation bu introducing a RL-based degradation-tolerant controlle
 r. The objectives are twofold: ensuring system stability despite degradati
 on\, and decelerating the degradation rate to complete missions and extend
  actuator life. This is achieved by imposing constraints on degradation ra
 tes using CBFs. Furthermore\, a cyclic off-policy algorithm is developed\,
  enabling iterative exploration and exploitation across multiple learning 
 cycles. This allows for continuous updates of neural network weights with 
 recent information on degradation levels\, ensuring that the learned polic
 y effectively stabilizes the system while accounting for degradation effec
 ts.\n\nRapporteurs :\n- Antoine GIRARD (Professor\, Université Paris Sacl
 ay)\n- Bayu JAYAWARDHANA (Professor\, Engineering and Technology Institute
  Groningen)\nExaminateurs :\n- Dalil ICHALAL (Professor\, Université d'Ev
 ry)\n- Bahare KIUMARSI (Assistant Professor\, Michigan State University)\n
 - Kyriakos VAMVOUDAKIS (Professor\, Georgia Institute of Technology)\n\nDi
 rectors :\n\nMayank Shekhar JHA (Maitre de Conférence\, Université de Lo
 rraine)\n\nDidier THEILLIOL (Professor\, Université de Lorraine)\n\n&nbsp
 \;\n\n&nbsp\;
CATEGORIES:Département CID,Soutenances thèses et HDR
LOCATION:Polytech Nancy\, 2 rue Jean Lamour\, Vandœuvre-lès-Nancy\, 54519
  \, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=2 rue Jean Lamour\, Vandœu
 vre-lès-Nancy\, 54519 \, France;X-APPLE-RADIUS=100;X-TITLE=Polytech Nancy
 :geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR