Relational, Object-Centric Agents for Completing Simulated Household Tasks with Wilka Carvalho - #402

Published: Aug. 20, 2020, 5:52 p.m.

Today we\u2019re joined by Wilka Carvalho, a PhD student at the University of Michigan, Ann Arbor. In our conversation, we focus on his paper \u2018ROMA: A Relational, Object-Model Learning Agent for Sample-Efficient Reinforcement Learning.\u2019 In the paper, Wilka explores the challenge of object interaction tasks, focusing on every day, in-home functions. We discuss how he\u2019s addressing the challenge of \u2018object-interaction\u2019 tasks, the biggest obstacles he\u2019s run into along the way.