Sheila McIlraith is a Professor in the Department of Computer Science, University of Toronto, a Canada CIFAR AI Chair (Vector Institute), and an Associate Director and Research Lead at the Schwartz Reisman Institute for Technology and Society. Prior to joining the University of Toronto, Prof. McIlraith spent six years as a Research Scientist at Stanford University, and one year at Xerox PARC. McIlraith’s research is in the area of sequential decision making, broadly construed, with a focus on human-compatible AI. She also has a particular interest in the ethics of AI and the impact of AI on society. McIlraith is a Fellow of the Association for Computing Machinery (ACM), a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), Associate Editor for the Journal of AI Research (JAIR), and a past Associate Editor of the Journal of Artificial Intelligence. McIlraith is past Program Co-Chair of the 32nd AAAI Conference on Artificial Intelligence (AAAI), the 13th International Conference on Principles of Knowledge Representation and Reasoning (KR2012), and the International Semantic Web Conference (ISWC2004), as well as past Conference Co-Chair of the 34th International Conference on Automated Planning and Scheduling (ICAPS). McIlraith and co-authors have received a number of paper awards from premier international venues including multiple tests-of-time awards, recognizing influential and impactful work.
Professor, Department of Computer Science, University of Toronto
Canada CIFAR Artificial Intelligence Chair
Associate Director and Research Lead at Schwartz Reisman Institute for Technology and Society
Research Interests
- Knowledge Representation & Automated Reasoning
- Reinforcement Learning
- Human-Compatible AI and AI Safety
- Sequential Decision Making
Highlights
- Fellow of the Association for Computing Machinery (ACM).
- Fellow of the Association for the Advancement of Artificial Intelligence (AAAI).
- Associate Editor of the Journal of Artificial Intelligence Research (JAIR).
Publications
Remembering to Be Fair: On Non-Markovian Fairness in Sequential Decision Making
2024
STEVE-1: A Generative Model for Text-to-Behavior in Minecraft
2023
Do Embedded Ethics Modules Have Impact Beyond the Classroom?
2022
You Can’t Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments
2022
Managing extreme AI risks amid rapid progress.
2024
Reward machines: Exploiting reward function structure in reinforcement learning
2022
LTL2action: Generalizing LTL instructions for multi-task rl
2021
Learning reward machines: A study in partially observable reinforcement learning
2021
Efficient multi-agent epistemic planning: Teaching planners about nested belief
2022
BLAST: Latent Dynamics Models from Bootstrapping
2021
Embedding Ethics in Computer Science Courses: Does it Work?
2022
Knowledge-based programs as building blocks for planning
2022
Explaining the Plans of Agents via Theory of Mind
2021
Be Considerate: Objectives, Side Effects, and Deciding How to Act
2021