News
The Tea Time Talks are back! Throughout the summer, take in 20-minute talks on early-stage ideas, prospective research and technical topics delivered by students, faculty and guests. Presented by Amii and the RLAI Lab at the University of Alberta, the talks are a relaxed and informal way of hearing leaders in AI discuss future lines of research they may explore.
Watch select talks from the third week of the series now:
Abstract: Designing adaptable control laws that can transfer between different robots is a challenge because of kinematic and dynamic differences, as well as in scenarios where external sensors are used. In this talk, Michael Przystupa explains his team’s work empirically investigating a neural network's ability to approximate the Jacobian matrix for an application in Cartesian control schemes. Specifically, they are interested in approximating the kinematic Jacobian, which arises from kinematic equations mapping a manipulator’s joint angles to the end-effector’s location.
Abstract: The way in which generalization is measured in Reinforcement Learning (RL) relies on concepts from supervised learning. Unlike a supervised learning model however, an RL agent must generalize across states, observations and actions from limited reward-based feedback. In this talk, Alex Lewandowski describes how their team reformulated the problem of generalization in RL within a single environment by considering contextual decision processes with observations from a supervised learning dataset. The result is an MDP that, while simple, necessitates function approximation for state abstraction while providing precise ground-truth labels for optimal policies and value functions. They then characterize generalization in RL across different axes: state-space, observation-space and action-space. Using the MNIST dataset with a contextual decision process, they rigorously evaluate generalization of DQN and QR-DQN in observation and action space with both online and offline learning.
This talk features a panel of reinforcement learning (RL) researchers -- all Amii Fellows, Canada CIFAR AI Chairs and UAlberta professors. Michael Bowling moderates this panel featuring Rich Sutton, Martha White, Patrick Pilarski and Rupam Mahmood.
Like what you’re learning here? Take a deeper dive into the world of RL with the Reinforcement Learning Specialization, offered by the University of Alberta and Amii. Taught by Martha White and Adam White, this specialization explores how RL solutions help solve real-world problems through trial-and-error interaction, showing learners how to implement a complete RL solution from beginning to end. Enroll in this specialization now!
May 16th 2024
News
Amii and New Harvest are excited to announce phase two of their research collaboration focused on applications of artificial intelligence and machine learning in cellular agriculture. The new phase initiates a year-long project with an open call to researchers and experts specializing in cellular agriculture and machine learning who want to apply ML solutions to solve the challenges in the field.
May 7th 2024
News
Check out the advancements being presented by Amii researchers at the 2024 International Conference on Learning Representation.
May 2nd 2024
News
Read our monthly update on Alberta’s growing machine intelligence ecosystem and exciting opportunities to get involved.
Looking to build AI capacity? Need a speaker at your event?