BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20210503T150000
DTEND;TZID=America/New_York:20210503T160000
DTSTAMP:20260406T224313
CREATED:20210426T195420Z
LAST-MODIFIED:20210426T195420Z
UID:4882-1620054000-1620057600@seasevents.nmsdev7.com
SUMMARY:ESE Seminar: "Demystifying the Efficiency of Reinforcement Learning: Two Recent Stories"
DESCRIPTION:Reinforcement learning (RL)\, which is frequently modeled as sequential learning and decision making in the face of uncertainty\, is garnering growing interest in recent years due to its remarkable success in practice. In contemporary RL applications\, it is increasingly more common to encounter environments with prohibitively large state and action space\, thus imposing stringent requirements on the sample and computational efficiency of the RL algorithms in use. Despite the empirical success\, however\, the theoretical underpinnings for many popular RL algorithms remain highly inadequate even for the tabular setting. \nIn this talk\, we present two vignettes regarding the effectiveness of RL algorithms. The first vignette demonstrates that a perturbed model-based RL approach is minimax optimal under a generative model\, without suffering from a sample size barrier that was present in all past work. The second vignette covers policy optimization in reinforcement learning. On the one hand\, we demonstrate that the popular softmax policy gradient method can take exponential time to converge; on the other hand\, employing natural policy gradients and enforcing entropy regularization provably achieve fast global convergence. These results cover two distinctive RL paradigms\, and might shed light on the efficacy of these algorithms in more complicated scenarios. \nFor the seminar link\, email Danielle T. Kopicko at dtadros@seas.upenn.edu.
URL:https://seasevents.nmsdev7.com/event/ese-seminar-demystifying-the-efficiency-of-reinforcement-learning-two-recent-stories/
LOCATION:https://upenn.zoom.us/j/96715197752
CATEGORIES:Seminar
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
END:VCALENDAR