To construct flexible systems that can adapt to the changing needs of daily operations, many researchers have proposed to construct robots that learn basic skills which can be re-used in multiple tasks and under varying conditions. In the machine learning community, hierarchical learning (HL) is designed to support skill abstraction and to provide a level of portability to acquired knowledge that improves performance on future tasks. These systems attempt to abstract the critical aspects of a task from multiple demonstrations such that the learned skill can be applied under varying environmental conditions and across different human co-workers.

While traditional hierarchical learning has been successfully applied to a number of real-world robotic tasks in which the robot acts autonomously and does not interact with humans, this method suffers a critical weakness when applied to collaborative scenarios. Division of responsibilities, role identification, and joint actions are left unaddressed, leaving state-of-the-art hierarchical systems inapplicable in collaborative domains. Social Hierarchical Learning (SHL) aims to address these weaknesses. Where traditional hierarchical learning assumes an isolated, autonomous robot which learns and performs on its own, Social Hierarchical Learning develops a collaborative robot that learns portable skills from human guidance and engages in tasks with human co-workers.

SHL leverages and extends the capabilities of state-of-the-art HL systems to operate under realistic human-robot interaction domains. Currently, HL lacks mechanisms to account for multi-agent coordination with humans in the loop, whereas SHL is designed explicitly for it. HL systems excel when presented tasks in which the agent has full environmental awareness and control. Such systems are not intended to handle elements outside the agent's control interacting within its problem space. At its core, SHL is designed to provide the required flexibility in task decomposition and assignment for successful human-robot collaboration.