AI Horizons: Interactive Learning and Control in the Era of Large Models By Dorsa Sadigh
COM3, School of ComputingThe talk delved into interactive learning, emphasizing learning objective functions from human feedback to capture preferences. It highlighted using large language models for value alignment and reward design in AI, extending beyond preference-based learning. The speaker discussed the importance of large pre-trained models in robotics, focusing on two aspects: pre-training for robotics tasks and using these models for more aligned AI agents. Key topics included "Voltron," a language-informed approach for robotics, and leveraging Large Language and Vision Models to understand human preferences and assist in teaching. The talk concluded with insights on how large models can identify and transform patterns, aiding in solving control problems.