BEGIN:VCALENDAR
PRODID;X-RICAL-TZSOURCE=TZINFO:-//Calagator//EN
CALSCALE:GREGORIAN
X-WR-CALNAME:Calagator
METHOD:PUBLISH
VERSION:2.0
BEGIN:VTIMEZONE
TZID;X-RICAL-TZSOURCE=TZINFO:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20120311T020000
RDATE:20120311T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
CREATED;VALUE=DATE-TIME:20120403T220133Z
DTEND;TZID=America/Los_Angeles;VALUE=DATE-TIME:20120409T111500
DTSTART;TZID=America/Los_Angeles;VALUE=DATE-TIME:20120409T101500
DTSTAMP;VALUE=DATE-TIME:20120403T220133Z
LAST-MODIFIED;VALUE=DATE-TIME:20120419T212040Z
UID:http://calagator.org/events/1250462229
DESCRIPTION:Abstract: &#13\;\n&#13\;\nAgents\, defined as programs or rob
 ots that interact with their environment\, are becoming increasingly com
 mon. However\, the current generation of agents are often unable to robu
 stly interact with each other\, or with humans\, severely limiting the n
 umber of tasks that they can accomplish. Furthermore\, these agents typi
 cally are unable to&#13\;\nadapt to their environment\, a critical skill
  when programmers do not have full knowledge of agents' future environme
 nts or when the agents' environment may change over time. This talk will
  discuss recent work in combining autonomous learning of sequential deci
 sion making tasks with transfer learning\, a general approach to sharing
  knowledge between agents with different capabilities\, resulting in sig
 nificant improvements to learning speeds and abilities.\n\nTags: psu\, c
 omputer science\, colloquium\, learning agents\n\nImported from: http://
 calagator.org/events/1250462229
URL:http://www.pdx.edu/computer-science/colloquium-and-other-events-0
SUMMARY:Real-Life Learning Agents
LOCATION:Portland State University FAB\, Room 86-09: 1900 SW Fourth Avenu
 e\, Portland Oregon 97201 US
SEQUENCE:2
END:VEVENT
END:VCALENDAR