BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Reinforcement Learning at Huawei: Robustness\, Safety\, and Effici
 ency - Haitham Ammar\, Huawei
DTSTART:20191030T100000Z
DTEND:20191030T110000Z
UID:TALK134230@talks.cam.ac.uk
CONTACT:Dr R.E. Turner
DESCRIPTION:Though successful in well-behaved and engineered environments\
 , current reinforcement learning methods suffer from robustness\, safety\,
  and efficiency-related issues when attempted in the real-world. In this t
 alk\, I will provide an overview of my team's work attempting to remedying
  some of the above issues. Precisely\, I discuss two novel methods we rece
 ntly developed attaining state-of-the-art results on a variety of simulate
 d robotic tasks.\n\nBio: \n\nHaitham leads the decision-making team at Hua
 wei technologies Research & Development UK. Prior to Huawei\, Haitham led 
 the reinforcement learning and tuneable AI team at PROWLER.io\, where he c
 ontributed numerously to their technology in finance and logistics.\n\n\nP
 rior to joining PROWLER.io\,  Haitham was an Assistant Professor in the Co
 mputer Science Department at the American University of Beirut (AUB). Befo
 re joining the AUB\, Haitham was a postdoctoral research associate in the 
 Department of Operational Research and Financial Engineering (ORFE) at Pri
 nceton University. Prior to Princeton\, Haitham conducted research in life
 long machine learning while being employed as a postdoctoral researcher at
  the University of Pennsylvania. Being a former member of the General Robo
 tics Automation Sensing and Perception (GRASP) lab\, he also contributed t
 o the application of machine learning to robotics.\n\n\n\nHaitham acquired
  his PhD in Artificial Intelligence (AI) at Maastricht University in the N
 etherlands. He shortened a four-year study in two after publishing over 30
  articles in world-leading AI and machine learning conferences and journal
 s. He attained his Masters in Mechatronics Engineering with a summa cum-la
 ude from the University of Applied Sciences in Ravensburg-Weingarten in Ge
 rmany. Being the basis for his Master studies\, Haitham acquired his Bache
 lors in Mechatronics Engineering from the Harriri Canadian University in L
 ebanon.\n\n\n\nHis primary research interests lie in the field of statisti
 cal machine learning and artificial intelligence\, focusing on lifelong le
 arning\, multitask learning\, knowledge transfer\, and reinforcement learn
 ing. He is also interested in learning using massive amounts of data over 
 extended time horizons - a property common to "Big-Data" problems. His res
 earch also spans different areas of control theory and nonlinear dynamical
  systems\, as well as social networks and distributed optimization.\n
LOCATION:Engineering Department\, CBL Room BE-438.
END:VEVENT
END:VCALENDAR