Robots Learn Increasingly Complex Tasks with Intrinsic Motivation and Automatic Curriculum Learning

TL;DR

This paper introduces SGIM-SAHT, a hierarchical reinforcement learning framework enabling robots to learn complex, multi-task sequences through intrinsic motivation, curriculum inference, and active imitation, advancing lifelong learning capabilities.

Contribution

The paper presents a novel hierarchical reinforcement learning framework that learns task hierarchies and curricula autonomously for multi-task robot learning.

Findings

Successfully infers task hierarchies and curricula

Enables robots to learn sequences of unbounded complexity

Integrates imitation learning with intrinsic motivation

Abstract

Multi-task learning by robots poses the challenge of the domain knowledge: complexity of tasks, complexity of the actions required, relationship between tasks for transfer learning. We demonstrate that this domain knowledge can be learned to address the challenges in life-long learning. Specifically, the hierarchy between tasks of various complexities is key to infer a curriculum from simple to composite tasks. We propose a framework for robots to learn sequences of actions of unbounded complexity in order to achieve multiple control tasks of various complexity. Our hierarchical reinforcement learning framework, named SGIM-SAHT, offers a new direction of research, and tries to unify partial implementations on robot arms and mobile robots. We outline our contributions to enable robots to map multiple control tasks to sequences of actions: representations of task dependencies, an intrinsically motivated exploration to learn task hierarchies, and active imitation learning. While learning the hierarchy of tasks, it infers its curriculum by deciding which tasks to explore first, how to transfer knowledge, and when, how and whom to imitate.