A Motivational Architecture for Open-Ended Learning Challenges in Robots

TL;DR

This paper presents H-GRAIL, a hierarchical architecture that enables robots to autonomously generate goals, learn skills, and adapt to changing environments, addressing key challenges in open-ended learning.

Contribution

The paper introduces H-GRAIL, an integrated hierarchical framework combining intrinsic motivations and learning mechanisms for open-ended robotic learning.

Findings

H-GRAIL successfully discovers new goals autonomously.

It learns skill sequences for complex tasks.

It adapts effectively to non-stationary environments.

Abstract

Developing agents capable of autonomously interacting with complex and dynamic environments, where task structures may change over time and prior knowledge cannot be relied upon, is a key prerequisite for deploying artificial systems in real-world settings. The open-ended learning framework identifies the core challenges for creating such agents, including the ability to autonomously generate new goals, acquire the necessary skills (or curricula of skills) to achieve them, and adapt to non-stationary environments. While many existing works tackles various aspects of these challenges in isolation, few propose integrated solutions that address them simultaneously. In this paper, we introduce H-GRAIL, a hierarchical architecture that, through the use of different typologies of intrinsic motivations and interconnected learning mechanisms, autonomously discovers new goals, learns the required skills for their achievement, generates skill sequences for tackling interdependent tasks, and adapts to non-stationary environments. We tested H-GRAIL in a real robotic scenario, demonstrating how the proposed solutions effectively address the various challenges of open-ended learning.