BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250726T063306EDT-4767uJKEge@132.216.98.100
DTSTAMP:20250726T103306Z
DESCRIPTION:ISS Informal Systems Seminar\n\nSpeaker: Vivek Borkar – Departm
 ent of Electrical Engineering\, Indian Institute of Technology Bombay\, In
 dia \n\n   \n\n\n\nPresentation on YouTube\n\nAbstract: This talk will dis
 cuss some of what I feel to be key issues in dealing with reinforcement le
 arning in non-Markovian environments\, drawing parallels with some classic
 al ideas in stochastic control. This will be used to motivate a particular
  objective\, viz.\, approximation of certain conditional laws\, which is v
 ery much in the tradition of control of POMDPs using belief states.\n\n\nB
 iography: Vivek Borkar is currently an emeritus faculty at the Indian Inst
 itute of Technology Bombay\, Mumbai. He studied electrical engineering at 
 IIT Bombay and subsequently did his M.S. and Ph.D. in resp. Case Western R
 eserve Uni. and Uni. of California at Berkeley. His interests are in stoch
 astic control and optimization\, covering theory\, algorithms and applicat
 ions.\n
DTSTART:20230113T163000Z
DTEND:20230113T173000Z
LOCATION:CA\, ZOOM
SUMMARY:Reinforcement Learning for Non-Markovian Environments
URL:/cim/channels/event/reinforcement-learning-non-mar
 kovian-environments-351642
END:VEVENT
END:VCALENDAR