This session explores the integration of Agent AI and Reinforcement Learning (RL) with human feedback to enhance household robots' intelligence and adaptability. Agent AI enables robots to make autonomous decisions, while RL with human feedback ensures they learn and improve based on user interactions and preferences. This combination allows robots to perform complex tasks with greater precision, personalization, and reliability.

Participants will learn how these technologies can be applied to create more intelligent, user-centric household robots that continuously adapt and refine their behavior. The session will cover AI models, training processes, and deployment strategies, focusing on using Kubernetes to manage the scalable, distributed computing resources required. Through real-world examples and live demonstrations, attendees will gain insights into building smarter household robots that not only execute tasks but also learn to perform them more effectively over time.