News


6/1/2021
Marlos C. Machado has been appointed as an Amii fellow and a Canada CIFAR AI Chair.

1/1/2021
Marlos C. Machado has joined the CS department and RLAI as an adjunct professor.

2/14/2020
Matt Taylor joins the CS department and RLAI as an associate professor.

12/9/2019
RLAI PIs Rupam Mahmood, Csaba Szepesvari, and Adam White awarded CIFAR Canada AI Chairs

10/31/2019
RLAI joins twitter. Follow us at @rlai_lab.

10/30/2019
The final module of the Reinforcement Learning Specialization on Coursera led by Adam White and Martha White is out!

9/1/2019
RLAI is involved in 11 NeurIPS papers this year.

7/13/2019
A. Rupam Mahmood will be joining the RLAI lab and University of Alberta as an assistant professor.

7/1/2019
Csaba Szepesvari will be returning to UoAlberta and RLAI and joining Deepmind Edmonton

About Us

Reinforcement Learning and Artificial Intelligence (RLAI) lab pursues artificial-intelligence by formulating it as a large optimal-control problem and approximately solving it using reinforcement-learning methods. Reinforcement learning is a new body of theory and techniques for optimal control that has been developed in the last twenty years primarily within the machine learning and operations research communities, and which have separately become important in psychology and neuroscience. Reinforcement learning researchers have developed novel methods to approximate solutions to optimal-control problems that are too large or too ill-defined for classical solution methods such as dynamic programming. For example, reinforcement-learning methods have obtained the best known solutions in such diverse automation applications as helicopter flying, elevator scheduling, playing Go, and resource-constrained scheduling.

The objectives of the RLAI research program are to create new methods for reinforcement learning that remove some of the limitations on its widespread application and to develop reinforcement learning as a model of intelligence that could approach human abilities. These objectives are pursued through mathematics, through computational experiments, through the development of robotic systems, and through the development and testing of computational models of natural learning processes.