BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1584
DTSTAMP:20250717T064935Z
SUMMARY:Specification-Guided Reinforcement Learning
DESCRIPTION:Speaker: Suguman Bansal (Georgia Institute of Technology)\n\nAb
 stract: \nReinforcement Learning (RL) is being touted to revolutionize the
  way we design systems. However\, a key challenge to reaching that holy gr
 ail comes from the lack of guarantees that the synthesized systems offer. 
 Logic and formal reasoning can address some of these issues ... or can the
 y? In this talk\, I will cover recent progress in using logical specificat
 ions in RL and discuss the challenges it faces moving forward.\n \nShort 
 Bio:Suguman Bansal is a is an assistant professor in the School of Compute
 r Science at Georgia Institute of Technology. Her research interests lie a
 t the intersection of Artificial Intelligence and Programming Languages. S
 pecifically\, she works on developing tools and techniques to improve the 
 quality of automated verification and synthesis of computational systems. 
 Her recent work concerns providing formal guarantees about learning-enable
 d systems with a focus on Reinforcement Learning.\nShe received her Ph.D. 
 (2020) and M.S. (2016) in Computer Science from Rice University\, and B.S.
  (with Honors) degree (2014) in Mathematics and Computer Science from Chen
 nai Mathematical Institute. She is the recipient of the Amazon Research Aw
 ard 2024\, ATVA Best Paper Award 2023\, MIT EECS Rising Stars 2021 and 201
 8\, Future Faculty Fellowship 2019\, Andrew Ladd Fellowship 2016\, and a G
 old Medal at the ACM Student Research Competition at POPL 2016.\n
URL:https://www.tcs.tifr.res.in/web/events/1584
DTSTART;TZID=Asia/Kolkata:20250718T110000
DTEND;TZID=Asia/Kolkata:20250718T120000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR