Fundamentals of Reinforcement Learning

Martha White is an Assistant Professor in the Department of Computing Sciences at the University of Alberta, where she specializes in developing algorithms for agents that learn continuously from streams of data, focusing on representation learning and reinforcement learning. As a Principal Investigator at the Alberta Machine Intelligence Institute (AMII) and director of the Reinforcement Learning and Artificial Intelligence Lab (RLAI), she is at the forefront of research aimed at enhancing adaptive learning systems. Martha holds a Ph.D. in Computing Science from the University of Alberta and has published extensively on topics related to machine learning, including over 40 papers in top-tier journals and conferences. Her commitment to advancing knowledge in AI is complemented by her passion for mentoring emerging researchers and promoting diversity in computing. Outside of her academic pursuits, Martha enjoys soccer, outdoor activities, cooking, and reading science fiction, reflecting her diverse interests beyond the realm of technology.

Adam White is an Assistant Professor in the Department of Computing Sciences at the University of Alberta and a Senior Research Scientist at DeepMind. His research centers on artificial intelligence, specifically on replicating or simulating human-level intelligence in both physical and simulated agents. Adam's work explores how intelligence can be modeled through reinforcement learning agents that interact with unknown environments, learning from scalar reward signals rather than explicit feedback. He has taught courses on Reinforcement Learning and Artificial Intelligence at both the University of Alberta and Indiana University, contributing to the education of future leaders in AI. As a Principal Investigator of the Reinforcement Learning and Artificial Intelligence Lab (RLAI) and a fellow at the Alberta Machine Intelligence Institute (AMII), Adam is dedicated to advancing the field through innovative research and practical applications. His contributions include developing new algorithms for reinforcement learning, creating the RL-Glue framework for reinforcement learning experiments, and demonstrating learning capabilities in mobile robots. Outside of academia, Adam enjoys playing Gaelic football and exploring the natural world, reflecting his diverse interests beyond his professional pursuits.