Explore the concept of aligning AI with human values through reinforcement learning in this 51-minute lecture from the 2023 Cooperative AI Summer School. Delivered by Yali Du, a Lecturer at King's College London, delve into the challenges and potential solutions for creating AI systems that exhibit cooperative and trustworthy behavior in intelligent decision-making tasks. Gain insights into Du's research on reinforcement learning, multi-agent cooperation, and social agency, including human-involved learning, safety, and ethics. Learn about the importance of aligning AI with diverse human perspectives and the role of reinforcement learning in achieving this goal. Discover how this approach can contribute to the development of AI systems that are beneficial and aligned with the values of society as a whole.