BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20231105T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20240310T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.2620.events_uoft_date.0@www.statistics.utoronto.ca
CREATED:20230907T180135Z
DESCRIPTION:\nWhen and Where: \nMonday, October 30, 2023 3:30 pm to 4:30 
 pm \n 9014 \n Ontario Power Generation \n 9-700 University ave, Toronto,
  ON M5G 1Z5 \n\nDescription: \nJoin us at the Statistical Sciences Applied
  Research and Education Seminar (ARES) with Martha WhiteAssociate Professo
 r Department of Computing Science, Alberta Machine Intelligence Institute
  (Amii) University of AlbertaFree Virtual Event | Registration Required Ta
 lk TitleReinforcement Learning in the Real World: Making Predictions Onlin
 e for Water Treatment AbstractIn this talk I will discuss how we used rein
 forcement-learning based prediction approaches for a real drinking-water t
 reatment plant. I will first describe this dataset, and highlight challen
 ges with seasonality, non- stationarity, partial observability, and het
 erogeneity across sensors and operation modes of the plant. I will then ex
 plain General Value Function (GVF) predictions—discounted cumulative sums 
 of observations–and highlight why they might be preferable to classical n-
 horizon predictions common in time series prediction. One important conclu
 sion from this work is to demonstrate the importance of learning in deploy
 ment: an agent trained purely offline with no online updating performs mor
 e poorly than an agent that learns online. I will conclude with some gener
 al learnings about using reinforcement learning for real systems. Speaker 
 ProfileMartha White is an Associate Professor of Computing Science at the 
 University of Alberta. Martha is a PI of Amii–the Alberta Machine Intellig
 ence Institute–which is one of the top machine learning centres in the wor
 ld, and a director of RLAI–the Reinforcement Learning and Artificial Inte
 lligence Lab at the University of Alberta. She holds a Canada CIFAR AI Cha
 ir and received IEEE’s AIs 10 to Watch in 2020. She has authored more than
  65 papers in top journals and conferences. Martha has served as an area c
 hair for top conferences in AI and ML, including ICML, NeurIPS, ICLR, 
 AAAI and IJCAI, as well as co-program chair for ICLR in 2020, and is an 
 associate editor for JMLR and TMLR. \n\nContact Information: \n Esther Ber
 zunza esther.berzunza@utoronto.ca 4166897271 CANSSI Ontario \n9-700 Univer
 sity ave, Toronto, ON M5G 1Z5 \n\nCategories \n Data Science ARES \n\nAu
 diences \n FacultyGraduate Students
DTSTART;TZID=America/New_York:20231030T153000
DTEND;TZID=America/New_York:20231030T163000
LAST-MODIFIED:20250401T204144Z
LOCATION:9-700 University ave, Toronto, ON M5G 1Z5
SUMMARY:Statistical Sciences ARES: Martha White
URL;TYPE=URI:https://www.statistics.utoronto.ca/events/statistical-sciences
 -ares-martha-white
END:VEVENT
END:VCALENDAR