MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

TL;DR

MT-Opt introduces a scalable multi-task reinforcement learning framework enabling a team of robots to learn, share, and generalize a diverse set of skills simultaneously, improving efficiency and adaptability in real-world tasks.

Contribution

The paper presents a novel scalable multi-task reinforcement learning system, MT-Opt, that allows continuous learning and sharing of skills across multiple robots and tasks.

Findings

Successfully learned 12 real-world tasks with 7 robots.

Demonstrated generalization to new, structurally similar tasks.

Enabled faster acquisition of new tasks by leveraging past experience.

Abstract

General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to acquire each skill makes the prospect of a generalist robot trained with RL daunting. In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks. In this framework new tasks can be continuously instantiated from previously learned tasks improving overall performance and capabilities of the system. To instantiate this system, we develop a scalable and intuitive framework for specifying new tasks through user-provided examples of desired outcomes, devise a multi-robot collective learning system for data collection that simultaneously collects experience for multiple tasks, and develop a scalable and generalizable multi-task deep reinforcement learning method, which we call MT-Opt. We demonstrate how MT-Opt can learn a wide range of skills, including semantic picking (i.e., picking an object from a particular category), placing into various fixtures (e.g., placing a food item onto a plate), covering, aligning, and rearranging. We train and evaluate our system on a set of 12 real-world tasks with data collected from 7 robots, and demonstrate the performance of our system both in terms of its ability to generalize to structurally similar new tasks, and acquire distinct new tasks more quickly by leveraging past experience. We recommend viewing the videos at https://karolhausman.github.io/mt-opt/