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: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
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20220323T150000
DTEND;TZID=America/New_York:20220323T160000
DTSTAMP:20260406T033433
CREATED:20220315T182009Z
LAST-MODIFIED:20220315T182009Z
UID:6535-1648047600-1648051200@seasevents.nmsdev7.com
SUMMARY:Spring 2022 GRASP SFI: Scott Guan\, Georgia Institute of Technology\, "Toward Scalability in Multi-Agent Decision Making"
DESCRIPTION:*This will be a HYBRID Event with in-person attendance in Levine 512 and Virtual attendance via Zoom \nWhile machine learning algorithms have led to tremendous improvements in many multi-agent domains\, scalability remains one of the major challenges for multi-agent decision-making. In this talk\, we will focus on two aspects of the scalability challenge: (i) number of agents\, and (ii) large state space. We will propose possible approaches to remedy both challenges. In the first part\, we introduce the mean-field approximation\, which simplifies the interactions among a large population of agents. We will present theoretical analysis and convergence results on a class of entropy-regularized mean-field games with optimality bounds. In the second part\, we address the large state space issue using two ideas: first\, the use of hierarchical decomposition to decompose the original game to a number of smaller games; and second\, the approximation of expensive operators (e.g.\, minimax) to reduce computation time in multi-agent reinforcement learning. Convergence analysis and application to pursuit-evasion games will also be discussed.
URL:https://seasevents.nmsdev7.com/event/spring-2022-grasp-sfi-scott-guan-georgia-institute-of-technology-toward-scalability-in-multi-agent-decision-making/
LOCATION:Levine 512
ORGANIZER;CN="General Robotics%2C Automation%2C Sensing and Perception (GRASP) Lab":MAILTO:grasplab@seas.upenn.edu
END:VEVENT
END:VCALENDAR