Reinforcement learning (RL) is a type of machine learning that focuses on allowing a physical or virtual agent to complete sequential decision-making tasks, such as video games. It has had many successes, but can be slow in practice, requiring large amounts of data. This project aims to speed up such learning problems by leveraging information from an existing agent. This existing agent need not be perfect the algorithm developed will leverage information from the existing agent whenever possible and learn to outperform it where it is suboptimal.
Model-free Reinforcement Learning (RL) has recently demonstrated its great potential in solving difficult intelligent tasks. However, developing a successful RL model requires an extensive model tuning and tremendous training samples. Theoretical analysis of these RL methods, more specifically policy optimization methods, only stay in a simple setting where the learning happens in the policy space. This project attempts to advance the analysis of the policy optimization methods to a more realistic setting in the parameter space.
Across Canada, many families struggle to find high quality, affordable child care. Most child care options for families are limited to daytime and weekday work hours; this creates even greater challenges for shiftworkers who rely on paid child care. When child care is not available, mothers usually bear the greatest burden as many women, whether parenting alone or with a partner, act as the default primary caregiver.
MatchWork enables non-profit employment support organizations to support marginalized people to find meaningful employment opportunities. This includes people with physical and mental challenges, veterans, new immigrants and refugees.
To enable the development of self-driving vehicles, an accurate characterization of automotive radar modules under various road or weather conditions is required to ensure reliability is maintained under all circumstances. With this fundamental building-block established, ACAMP will be able to support Canadian technology companies in the development of autonomous vehicles.
Dust generated from haul roads poses a health and safety threat to mine sites. Traditionally, water has been applied on mine haul roads to control the dust. Using chemical surfactants to form a solution of chemical suppressants has been considered as a more effective method to control fugitive.
The rapid development in the areas of statistics and machine learning demonstrate unprecedented performance in making cognitive business decisions. Quartic.ai aims to use state-of-the-art machine learning technology to help manufacturers assess and maintain the quality of their industrial units, which suffer damage due to continuous usage and normal wear and tear. Such damage needs to be detected early to prevent further losses. The data in this domain are recorded using sensors at various stages in the process flow.
When we research the knowledge of the past, we also research the conditions of possibility for different futures (Foucault, 2003; Peers, 2015). Therefore, the purpose of this research project is to use the traces of the past to question the practices that have come to be naturalized within Alberta’s recreation system (e.g., providing pay-per-use recreation opportunities in big box facilities). Using an intensive archival research process, as well as a series of ongoing community conversations, we hope to uncover what is problematic and dangerous in recreation’s practices and discourses.