Rethinking AI Agents: Human-Centered Reinforcement Learning - Stephanie Milani

Abstract: AI agents will soon be as commonplace as smartphones. These agents will make sequences of interconnected decisions that impact human lives—from serving as decision support in healthcare to shaping educational paths for millions of students. A defining challenge for the future of AI is how to build agents that can effectively operate in and adapt to these human environments. In this talk, Stephanie shows how human-centered reinforcement learning offers a promising approach to developing better AI agents. She shows how we can leverage human-centered design to build realistic patient simulations that align with real-world needs. However, real-world tasks are often too complex to be fully defined with hand-crafted rules, making human feedback an essential tool for AI learning. To address this, Stephanie highlights their work on building a benchmark for learning from human feedback. Then, turning to the goal of AI transparency, she shows how we can learn human-understandable decision-making policies. Together, this work illustrates how human-centered reinforcement learning is a valuable approach for developing AI agents that can learn from and for the people whose lives they impact. Bio: Stephanie Milani is a final-year Ph.D. candidate in the Machine Learning Department at Carnegie Mellon University. Her research focuses on building reinforcement learning agents to address human-centered and use-case-inspired challenges. Stephanie is a 2024 Future Leader in Responsible Data Science & AI and Rising Star in Data Science. Her research has been published at top machine learning and human-computer interaction venues, including ICLR, NeurIPS, and CHI. It also received an outstanding paper award at the ICML MFM-EAI workshop and a best paper award at the NeurIPS GenAI4Health workshop. Outside of research, she received the CMU Machine Learning TA award, co-organized the MineRL international competition series at NeurIPS, and received the Newman Civic Fellowship for her service to computer science education.