Relational, Object-Centric Agents for Completing Simulated Household Tasks with Wilka Carvalho

Today we're joined by Wilka Carvalho, a PhD student at the University of Michigan, Ann Arbor. We first met Wilka at the Black in AI workshop at last year's NeurIPS conference, and finally got a chance to catch up about his latest research, ‘ROMA: A Relational, Object-Model Learning Agent for Sample-Efficient Reinforcement Learning.' In the paper, Wilka explores the challenge of object interaction tasks, focusing on every day, in-home functions like filling a cup of water in a sink. In our conversation, we discuss his interest in understanding the foundational building blocks of intelligence, how he's addressing the challenge of ‘object-interaction' tasks, the biggest obstacles he's run into along the way.