Demonstration-Bootstrapped Autonomous Practicing via Multi-Task Reinforcement Learning

TL;DR

This paper presents a reinforcement learning system that uses multi-task bootstrapping with prior data to enable autonomous practice in robots, reducing human intervention and solving complex long-term tasks.

Contribution

It introduces a method for bootstrapping multi-task policies and task sequencing with prior data, facilitating autonomous learning with minimal resets.

Findings

Effective in simulation and real-world kitchen tasks

Reduces resets and human intervention during training

Successfully learns temporally extended behaviors

Abstract

Reinforcement learning systems have the potential to enable continuous improvement in unstructured environments, leveraging data collected autonomously. However, in practice these systems require significant amounts of instrumentation or human intervention to learn in the real world. In this work, we propose a system for reinforcement learning that leverages multi-task reinforcement learning bootstrapped with prior data to enable continuous autonomous practicing, minimizing the number of resets needed while being able to learn temporally extended behaviors. We show how appropriately provided prior data can help bootstrap both low-level multi-task policies and strategies for sequencing these tasks one after another to enable learning with minimal resets. This mechanism enables our robotic system to practice with minimal human intervention at training time while being able to solve long horizon tasks at test time. We show the efficacy of the proposed system on a challenging kitchen manipulation task both in simulation and in the real world, demonstrating the ability to practice autonomously in order to solve temporally extended problems.