AI Seminar 2020: Craig Sherstan, Representation and General Value Functions (Aug 28)

Research Scientist at Sony AI and Amii alumnus Craig Sherstan presents "Representation and General Value Functions" at the AI Seminar (August 28, 2020).

The Artificial Intelligence (AI) Seminar is a weekly meeting at the University of Alberta where researchers interested in AI can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems, are explored.

Bio: Craig Sherstan is currently a Research Scientist at Sony AI, and defending his dissertation as a PhD student in Computing Science at the University of Alberta. He is supervised by Patrick Pilarski as part of the Bionic Limbs for Improved Natural Control (BLINC) Lab and the Reinforcement Learning and Artificial Intelligence Lab (RLAI), and is a Vanier Scholar. Craig’s research has focused on developing agents which can continually and incrementally construct predictive representations of themselves and their world.

Abstract: Research in artificial general intelligence aims to create agents that can learn from their own experience to solve arbitrary tasks in complex and dynamic settings. To do so effectively and efficiently, such an agent must be able to predict how its environment will change both dependently and independently of its own actions. General value functions (GVFs) are one approach to representing such relationships. A single GVF poses a predictive question defined by three components: a behavior (policy), a prediction timescale, and a prediction target (cumulant). Estimated answers to these questions can be learned efficiently from the agent’s own experience using temporal-difference learning methods. The agent’s collection of GVF questions and corresponding answers can be viewed as forming a predictive model of the agent’s interaction with its environment. Ultimately, such a model may enable an agent to understand its environment and make decisions therein.