BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Australia/Sydney BEGIN:DAYLIGHT DTSTART:20221002T030000 TZOFFSETFROM:+1000 TZOFFSETTO:+1100 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=10 TZNAME:AEDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20220403T020000 TZOFFSETFROM:+1100 TZOFFSETTO:+1000 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4 TZNAME:AEST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220907T072421Z UID:A87AF80B-DC94-4605-A1F4-8584B2E38A2B DTSTART;TZID=Australia/Sydney:20220907T150000 DTEND;TZID=Australia/Sydney:20220907T160000 DESCRIPTION:IEEE Computational Intelligence Society\, Australian Capital Te rritory (ACT) chapter invites you to:\n\nSeminar (in-person): 07 September 2022\, 3.00-4.00 pm AEST (Canberra time)\n\nSpeaker: Professor Garrison G reenwood\, Portland State University\, USA\n\nTitle: Evolving Players for the Generalized Divide the Dollar Game\n\nVenue: LTN 08\, Building 32 (Lec ture Theatre North)\, UNSW Canberra\, Northcott Drive\, ACT\n\n===\n\nAbst ract:\n\nDivide the dollar is a simpler version of a game invented by John Nash to study the bargaining problem. Two players simultaneously state (b id) how much of a dollar they will accept. If the bid total is less than o r equal to $1\, they get their bid as a payoff. Otherwise\, both players g et nothing. The generalized divide the dollar game is an n-player version that will also\, under limited circumstances\, allow for small subsidies. In this talk I describe how players for an n=3 player game\, implemented a s neural networks\, can be co-evolved. Both Differential Evolution and CMA -ES versions of the co-evolution are discussed along with an analysis on w hy one evolutionary algorithm achieved better results. But co-evolving neu ral network players\, although highly successful\, becomes computationally expensive as n grows. A second evolutionary algorithm approach\, using a completely different genome\, is discussed and results are presented. This second method can successfully evolve 20 or more players with small compu tational effort.\n\n===\n\nSpeaker biography:\n\nGarrison Greenwood receiv ed a Ph.D. in Electrical Engineering from the University of Washington\, S eattle\, WA. After spending more than a decade in industry designing multi processor embedded systems\, he entered academia. He is currently a profes sor in the Electrical and Computer Engineering Department at Portland Stat e University\, Portland\, OR. Dr. Greenwood has a long history of support of the IEEE Computational Intelligence Society including serving as the ge neral chair of the IEEE Congress on Evolutionary Computation conference (2 004 and 2012) and 4 years as the CIS Vice President of Conferences. From 2 009 through 2014 he was the Editor-in-Chief of the IEEE Transactions on Ev olutionary Computation. His research interests are evolvable hardware and mathematical game theory. Dr. Greenwood is a registered professional engin eer in the State of California\, USA.\n\n============\n\nBldg: Lecture The atre North (Building 32)\, LTN 08\, UNSW Canberra\, Northcott Drive\, Canb erra\, Australian Capital Territory\, Australia\, 2602 LOCATION:Bldg: Lecture Theatre North (Building 32)\, LTN 08\, UNSW Canberra \, Northcott Drive\, Canberra\, Australian Capital Territory\, Australia\, 2602 ORGANIZER:h.singh@adfa.edu.au SEQUENCE:3 SUMMARY:IEEE CIS Seminar: Evolving Players for the Generalized Divide the D ollar Game / Prof. Garrison Greenwood URL;VALUE=URI:https://events.vtools.ieee.org/m/323266 X-ALT-DESC:Description: <br /><p>IEEE Computational Intelligence Society\, Australian Capital Territory (ACT) chapter invites you to:&nbsp\;</p>\n<p> Seminar (in-person): 07 September 2022\, 3.00-4.00 pm AEST (Canberra time) </p>\n<p>Speaker: Professor Garrison Greenwood\, Portland State University \, USA</p>\n<p>Title:&nbsp\;Evolving Players for the Generalized Divide th e Dollar Game</p>\n<p>Venue: LTN 08\, Building 32 (Lecture Theatre North)\ , UNSW Canberra\, Northcott Drive\, ACT</p>\n<p>===</p>\n<p><strong>Abstra ct: &nbsp\;</strong></p>\n<p>Divide the dollar is a simpler version of a g ame invented by John Nash to study the bargaining problem. Two players sim ultaneously state (bid) how much of a dollar they will accept. If the bid total is less than or equal to $1\, they get their bid as a payoff. Otherw ise\, both players get nothing. The generalized divide the dollar game is an n-player version that will also\, under limited circumstances\, allow f or small subsidies.&nbsp\;In this talk I describe how players for an n=3 p layer game\, implemented as neural networks\, can be co-evolved. Both Diff erential Evolution and CMA-ES versions of the co-evolution are discussed a long with an analysis on why one evolutionary algorithm achieved better re sults.&nbsp\; But co-evolving neural network players\, although highly suc cessful\, becomes computationally expensive as n grows. A second evolution ary algorithm approach\, using a completely different genome\, is discusse d and results are presented. This second method can successfully evolve 20 or more players with small computational effort.</p>\n<p>===</p>\n<p><str ong>Speaker biography:&nbsp\;</strong></p>\n<p>Garrison Greenwood received a Ph.D. in Electrical Engineering from the University of Washington\, Sea ttle\, WA. After spending more than a decade in industry designing multipr ocessor embedded systems\, he entered academia. He is currently a professo r in the Electrical and Computer Engineering Department at Portland State University\, Portland\, OR. Dr. Greenwood has&nbsp\;a long history of supp ort of the IEEE Computational Intelligence Society including serving as th e general chair of the IEEE Congress on Evolutionary Computation conferenc e (2004 and 2012) and 4 years as the CIS Vice President of Conferences. Fr om 2009 through 2014 he was the Editor-in-Chief of the IEEE Transactions o n Evolutionary Computation. His research interests are evolvable hardware and mathematical game theory. Dr. Greenwood is a registered professional e ngineer in the State of California\, USA.</p>\n<p>============</p>\n<p>&nb sp\;</p> END:VEVENT END:VCALENDAR