Grant: Canada Research Chairs
University of Alberta
$120,000.00
Reinforcement Learning
FY 2024-25
Summary
Our systems are getting smarter. We have smart assistants, the ability to command our devices using voice, improved recommendations and smart home devices like vacuums. This automation has made our lives better, but has yet to spread to many areas of our lives and in some cases is not always that smart. For many important systems in our lives, like our drinking water treatment facilities, traditional (non-learning and non-automated) approaches are still the norm. There is huge potential to improve these industrial control systems with adaptive, learning systems, reducing energy use, saving money and potentially making our environment healthier for everyone.
Dr. Martha White is developing machine learning systems for this goal: to allow the systems we interact with on a daily basis to be constantly adapting and improving. The goal is to leverage what machine learning does best: learning for high-volumes of high-dimensional data. People have a hard time monitoring many sensors, for example, but are skilled at making high-level decisions. Our learning machines, on the other hands, can monitor and learn from many many sensors. Low-level decisions can be improved with machine learning, with critical high-level decisions left to people. For example, water treatment operators can focus on high-level decisions, such as what chemicals to use. The agent can improve efficiency and reduce chemical usage, using high-dimensional sensory information about the system and water conditions. A unique part of this research program is a focus on system that continually learn in deployment, which is currently a big challenge but also a critical component of an adaptive, robust learning system.
Dr. White is internationally recognized as a leader in this area. She has published 50+ papers in top venues in machine learning, focused on algorithm development for using learning systems. She is frequently invited to give talks about her advances, and was recognized for her work by the IEEE in 2020 with the “AIs 10 to Watch: The Future of AI” award.
Program
Canada Research Chairs
Recipient
Location
Alberta, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
CRC-2022-00175
Name nom
White, Martha
Department département
Computing Science - University of Alberta
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2022
Award amount
120000
Program id
CRC
Program name en
Canada Research Chairs
Program name fr
Chaires de recherche du Canada
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
9998
Committee name en
Canada Research Chair Selection Committee
Committee name fr
Comité de sélection des Chaires de recherche du Canada
Area of application code
9999
Area of application group en
Not available
Area of application group fr
Non disponible
Area of application en
Not available
Area of application fr
Non disponible
Research subject code
9999
Research subject group en
Not available
Research subject group fr
Non disponible
Research subject en
Not available
Research subject fr
Non disponible
Field of research list codes
RDF1020104
Field of research list names en
Machine learning
Field of research list names fr
Apprentissage machine
Socioeconomic objective list codes
RDS10610
Socioeconomic objective list names en
Information systems, technologies and services
Socioeconomic objective list names fr
Systèmes, technologies et services d'information
Application title
Reinforcement Learning
Keywords
machine learning; reinforcement learning; representation learning; continual learning; off-policy learning
Application summary
Our systems are getting smarter. We have smart assistants, the ability to command our devices using voice, improved recommendations and smart home devices like vacuums. This automation has made our lives better, but has yet to spread to many areas of our lives and in some cases is not always that smart. For many important systems in our lives, like our drinking water treatment facilities, traditional (non-learning and non-automated) approaches are still the norm. There is huge potential to improve these industrial control systems with adaptive, learning systems, reducing energy use, saving money and potentially making our environment healthier for everyone.
Dr. Martha White is developing machine learning systems for this goal: to allow the systems we interact with on a daily basis to be constantly adapting and improving. The goal is to leverage what machine learning does best: learning for high-volumes of high-dimensional data. People have a hard time monitoring many sensors, for example, but are skilled at making high-level decisions. Our learning machines, on the other hands, can monitor and learn from many many sensors. Low-level decisions can be improved with machine learning, with critical high-level decisions left to people. For example, water treatment operators can focus on high-level decisions, such as what chemicals to use. The agent can improve efficiency and reduce chemical usage, using high-dimensional sensory information about the system and water conditions. A unique part of this research program is a focus on system that continually learn in deployment, which is currently a big challenge but also a critical component of an adaptive, robust learning system.
Dr. White is internationally recognized as a leader in this area. She has published 50+ papers in top venues in machine learning, focused on algorithm development for using learning systems. She is frequently invited to give talks about her advances, and was recognized for her work by the IEEE in 2020 with the “AIs 10 to Watch: The Future of AI” award.
