BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20190310T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20191103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20190517T154835Z UID:F8BE989C-7D0D-4FE9-8672-2BA87B7F2ADD DTSTART;TZID=America/Los_Angeles:20190516T180000 DTEND;TZID=America/Los_Angeles:20190516T200000 DESCRIPTION:A technical program starting at 6:30PM with refreshments and ne tworking from 6:00 to 6:30.\n\nTechnical Abstract: Reinforcement learning methods have been steadily gaining popularity within the machine-learning community as an approach to learn gaming strategy through trial and error. One of the downsides of classical reinforcement learning is the limited a pplicability to games with a large state spaces which has resulted in the adoption of deep learning methods to approximate value functions defined o ver the state. However learning can still be difficult for complex games\, particularly for those with a large stochastic component that can results in similar strategies having very different outcomes. In this work a deep reinforcement learning algorithm is presented to address these issues as seen in a representative dice based multi-player game known as Qwixx. With out knowing any rules about the game the algorithm eventually learns winni ng strategies by playing against a human generated method based on optimal control.\n\nCo-sponsored by: CH06204 - San Diego Section Chapter\, CIS11\ n\nSpeaker(s): Dr. Gideon Prior\, \n\nAdvanced Test Equipment Rentals\, 10 401 Roselle Street\, San Diego\, California\, United States\, 92121 LOCATION:Advanced Test Equipment Rentals\, 10401 Roselle Street\, San Diego \, California\, United States\, 92121 ORGANIZER:scstubberud@ieee.org SEQUENCE:3 SUMMARY:Deep Reinforcement Learning Applied to the Game of Qwixx URL;VALUE=URI:https://events.vtools.ieee.org/m/198105 X-ALT-DESC:Description: <br /><p>A technical program starting at 6:30PM&nbs p\; with refreshments and networking from 6:00 to 6:30.</p>\n<p>Technical Abstract:&nbsp\; Reinforcement learning methods have been steadily gaining popularity within the machine-learning community as an approach to learn gaming strategy through trial and error. One of the downsides of classical reinforcement learning is the limited applicability to games with a large state spaces which has resulted in the adoption of deep learning methods to approximate value functions defined over the state. However learning ca n still be difficult for complex games\, particularly for those with a lar ge stochastic component that can results in similar strategies having very different outcomes. In this work a deep reinforcement learning algorithm is presented to address these issues as seen in a representative dice base d multi-player game known as Qwixx. Without knowing any rules about the ga me the algorithm eventually learns winning strategies by playing against a human generated method based on optimal control.&nbsp\;</p> END:VEVENT END:VCALENDAR