Our weekly SRI Seminar Series welcomes Sheila McIlraith, associate director and research lead at the Schwartz Reisman Institute, professor in the Department of Computer Science at the University of Toronto, and a Canada CIFAR AI Chair and faculty member at the Vector Institute for Artificial Intelligence. Prior to joining U of T, McIlraith spent six years as a research scientist at Stanford University, and one year at Xerox PARC. McIlraith is the author of over 100 scholarly publications in the area of knowledge representation, automated reasoning and machine learning. Her work focuses on AI sequential decision making broadly construed, through the lens of human-compatible AI.
In this talk, McIlraith will explore how AI safety can be enhanced by ensuring that reinforcement learning agents adhere to greater consideration of their environments as a guiding principle, and what such formulations of enhanced consideration might look like.
Talk title:
“Can ‘being considerate’ lead to safer AI?”
Abstract:
Recent work in AI safety has highlighted that in sequential decision making, objectives are often underspecified or incomplete. This gives discretion to the acting agent to realize the stated objective in ways that may result in undesirable or even catastrophic outcomes. We contend that to learn to act safely, a reinforcement learning (RL) agent should include contemplation of the impact of its actions on the wellbeing and agency of others in the environment, including other acting agents and reactive processes. Indeed, in some instances such agents may have a moral or legal obligation to do so. In this talk, I'll introduce the idea of "being considerate" in the context of AI safety and propose a few simple ways of endowing RL agents with such a capability. I'll also discuss different formulations of being considerate, or differentially considerate to different agents, manifesting behaviour that ranges from self-centred to self-less, as demonstrated by some simple evocative experiments.
Suggested reading:
D. Amodei, C. Olah, J. Steinhardt, P.F. Christiano, J. Schulman, D. Mané, “Concrete Problems in AI Safety.” CoRR abs/1606.06565, 2016.
About Sheila McIlraith
Sheila McIlraith is a professor in the Department of Computer Science, University of Toronto, Canada CIFAR AI Chair and faculty member at the Vector Institute for Artificial Intelligence, and associate director and research lead at the Schwartz Reisman Institute for Technology and Society. Prior to joining U of T, McIlraith spent six years as a research scientist at Stanford University, and one year at Xerox PARC. McIlraith is the author of over 100 scholarly publications in the area of knowledge representation, automated reasoning and machine learning. Her work focuses on AI sequential decision making broadly construed, through the lens of human-compatible AI. McIlraith is a fellow of the Association for Computing Machinery (ACM), a fellow of the Association for the Advancement of Artificial Intelligence (AAAI) and a past President of KR Inc., the international scientific foundation concerned with fostering research and communication on knowledge representation and reasoning. She is currently serving on the Standing Committee of the Stanford One Hundred Year Study on Artificial Intelligence (AI100). McIlraith is an associate editor of the Journal of Artificial Intelligence Research (JAIR), a past associate editor of the journal Artificial Intelligence (AIJ), and a past board member of Artificial Intelligence Magazine. In 2018, McIlraith served as program co-chair of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18). She also served as program co-chair of the International Conference on Principles of Knowledge Representation and Reasoning (KR2012), and the International Semantic Web Conference (ISWC2004). McIlraith's early work on Semantic Web Services has had notable impact. In 2011, she and her co-authors were honoured with the SWSA 10-year Award, recognizing the highest impact paper from the International Semantic Web Conference, 10 years prior. Her research has also made practical contributions to the development of next-generation NASA space systems and to emerging Web standards.
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by 45 minutes of discussion. Registered attendees will be emailed a Zoom link approximately one hour before the event begins. The event will be recorded and posted online.
Sheila McIlraith