BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Safe Guaranteed Exploration for Non-linear Systems
DTSTART:20261204T140000
DTEND:20261204T150000
DTSTAMP:20261003T200334Z
UID:ac26c0235273ac4c99018a2d2b540b785854835116c5b648a55374a6
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr Manish Prajapat Ph.D. reinforcement learning and control fr
 om ETH Zurich\n\nWinner of the IEEE CSS Young Author Best Journal Paper Aw
 ard 2026\nAbstract: \nSafely exploring environments with a-priori unknown
  constraints is a fundamental challenge that restricts the autonomy of rob
 ots. While safety is paramount\, guarantees on sufficient exploration are 
 also crucial for ensuring autonomous task completion. To address these cha
 llenges\, we propose a novel safe guaranteed exploration framework using o
 ptimal control\, which achieves first-of-its-kind results: guaranteed expl
 oration for non-linear systems with finite time sample complexity bounds\,
  while being provably safe with arbitrarily high probability. The framewor
 k is general and applicable to many real-world scenarios with complex non-
 linear dynamics and unknown domains. For efficient implementation\, we exp
 loit goal-directed exploration\, and receding-horizon replanning while pre
 serving the framework’s guarantees\, and demonstrate safe\, efficient ex
 ploration in challenging unknown environments using a car model.\n\nBiogra
 phy: \nManish Prajapat earned his Ph.D. in reinforcement learning and con
 trol from ETH Zurich in May 2026. He was a Doctoral Fellow at the ETH AI C
 enter working with Prof. Melanie Zeilinger and Prof. Andreas Krause. Previ
 ously\, he earned his master’s degree in Robotics\, Systems\, and Contro
 l from ETH Zurich and was a visiting scholar at Caltech. He received his b
 achelor’s degree from the Indian Institute of Technology (IIT) Madras in
  2017. At IIT Madras\, he was honored as the Best Graduating Student (Co-c
 urricular) in 2017 and received the Sivasailam Merit Prize for the best th
 esis. His research interests are sequential decision-making under complex 
 scenarios\, e.g.\, non-Markovian objectives\, unknown constraints or unkno
 wn dynamics of non-linear systems.\n\n 
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405 https://epfl.
 zoom.us/j/69006439273
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR