Abstract:
This talk explores the speculative question: what if current or future AI systems have qualia, such as pain or pleasure? It does so by assuming that AI systems might someday possess qualia—and that the quality of these subjective experiences should be considered alongside performance metrics. Concrete mathematical problem settings, inspired by reinforcement learning formulations and theories from philosophy of mind, are then proposed and initial approaches and properties are presented. This talk serves as an introduction to the paper “Qualia Optimization”.
Bio:
Philip Thomas is an associate professor and the Doctoral Program Director at the Manning College of Information and Computer Sciences at the University of Massachusetts. He has published at top venues, including Science, is president and co-founder of the Reinforcement Learning Conference, and has testified before the US House Committee on Financial Services’ Task Force on Artificial Intelligence. He received his PhD from the University of Massachusetts, where he studied reinforcement learning (RL) under the supervision of Prof. Andy Barto. His research initially focused on policy gradient algorithms, off-policy evaluation, confidence intervals, high-confidence safety guarantees for RL, and fairness; more recently, it has shifted toward the intersection of RL and the philosophy of mind.
Orchard View Room
Philip Thomas, University of Massachusetts