Date of this Version
Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani, Edgar Dobriban, James Weimer, and Julia Parish-Morris, "Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates", 6th Conference on Robot Learning . November 2022.
Long horizon robot learning tasks with sparse rewards pose a significant challenge for current reinforcement learning algorithms. A key feature enabling humans to learn challenging control tasks is that they often receive expert intervention that enables them to understand the high-level structure of the task before mastering low-level control actions. We propose a framework for leveraging expert intervention to solve long-horizon reinforcement learning tasks. We consider option templates, which are specifications encoding a potential option that can be trained using reinforcement learning. We formulate expert intervention as allowing the agent to execute option templates before learning an implementation. This enables them to use an option, before committing costly resources to learning it. We evaluate our approach on three challenging reinforcement learning problems, showing that it outperforms state-of-the-art approaches by two orders of magnitude.
CPS Safe Autonomy, CPS Machine Learning
6th Conference on Robot Learning
Sample-Efficient Reinforcement Learning, Expert Intervention, Options, Planning with Primitives
Date Posted:28 December 2022
This document has been peer reviewed.