BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Churchill CompSci Talks
SUMMARY:AI in Board Games 2: The Settlers of Catan - Benja
 min Naccarato\, Churchill College
DTSTART;TZID=Europe/London:20160120T194000
DTEND;TZID=Europe/London:20160120T203000
UID:TALK62541AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/62541
DESCRIPTION:Settlers of Catan is a modern board game\, where 3
 –4 players collect resources to build and trade wi
 th each other\, in order to be the first to reach 
 a set number of points. This game presents interes
 ting difficulties for an AI\, including randomness
 \, hidden information\, negotiation and trading.\n
 In this talk\, I shall discuss the implementations
  presented to handle these considerations. We will
  begin with the AI implementation in the JSettlers
  game and the later improvements to this agent\, a
 nd follow by reviewing the benefits of using Monte
 -Carlo Tree Search or a Reinforcement Learning app
 roach in this context\, ending with a closer look 
 at the trading AI. By following the contributions 
 by researchers towards a competent Settlers AI\, w
 e shall explore the concepts behind various AI alg
 orithms and techniques\, and the process of improv
 ing upon established work.
LOCATION:Wolfson Hall\, Churchill College
CONTACT:Matthew Ireland
END:VEVENT
END:VCALENDAR