Practice Makes Perfect: Planning to Learn Skill Parameter Policies

Nishanth Kumar, Tom Silver, Willie McClinton, Linfeng Zhao, Stephen Proul, Tomás Lozano-Pérez, Leslie Kaelbling, Jennifer Barry
February 2024
PDF Code Project Video Press (MIT News)

Abstract

We enable a robot to rapidly and autonomously specialize parameterized skills by planning to practice them. The robot decides what skills to practice and how to practice them. The robot is left alone for hours, repeatedly practicing and improving.

Type
Conference paper
Publication
In RSS 2024
Planning Planning to Learn Robot Planning Robot Learning Parameterized Skills Bilevel Planning Task and Motion Planning TAMP
Linfeng Zhao
Linfeng Zhao
CS Ph.D. Student

I am a CS Ph.D. student at Khoury College of Computer Sciences of Northeastern University, advised by Prof. Lawson L.S. Wong. My research interests include reinforcement learning, artificial intelligence, and robotics.

Related