BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-9c4ab73ab173dbacc3fa5849e0b20922@cmc.deusto.eus
DTSTART:20201211T070000Z
DTEND:20201211T170000Z
DTSTAMP:20251031T223800Z
RDATE;VALUE=PERIOD:20200908T080000Z/20200908T213000Z,20200916T220000Z/20200917T110000Z,20200923T220000Z/20200924T110000Z,20200930T220000Z/20201001T110000Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:CCM Course: Inverse problems in Reinforcement Learning
DESCRIPTION:Carlos Esteve Yague Postdoctoral researcher from CCM Deusto will present the CCM course “An Introduction to Reinforcement Learning and Optimal Control Theory ( https://cmc.deusto.eus/an-introduction-to-reinforcement-learning-and-optimal-control-theory/ )” for this month in four sessions:\nSpeaker: Carlos Esteve Yague, ( https://cmc.deusto.eus/carlos-esteve-yague/ ) Postdoctoral Researcher at CCM\nFrom September 8th. to October 1st, 2020\nSessions: 4, one session/week\nAbstract. This mini-course aims to be an introduction to Reinforcement Learning for people with a background in control theory. We will discuss the differences and similarities between the two settings, relying on Markov decision processes (MDP) and dynamical systems (DS) respectively. We will present and analyze the most elementary Reinforcement Learning techniques, based on the dynamic programming principle. By means of the HJB equation, we will also discuss the possibility of implementing RL methods in continuous settings. Finally, we will consider inverse problems arising in this context, where the goal is to identify the underlying dynamics of the system and/or a cost functional compatible with a given optimal policy.\nSessions planning:\n  Introduction and Dynamic Programming Methods\n  From discrete to continuous models, Hamilton-Jacobi-Bellman equations\n  Q-Learning\n  Inverse problems in Reinforcement Learning\n \n
URL:https://cmc.deusto.eus/events-calendar/ccm-course-inverse-problems-in-reinforcement-learning/
CATEGORIES:Course
ATTACH;FMTTYPE=image/jpeg:https://cmc.deusto.eus/wp-content/uploads/ccm-course-robotic_surgery.jpg
END:VEVENT
END:VCALENDAR