Cycle-of-Learning for Autonomous Systems from Human Interaction
This work addresses the challenge of improving human-robot interaction for training autonomous systems, but it appears incremental as it builds on existing paradigms without claiming major breakthroughs.
The paper tackles the problem of training end-to-end reinforcement learning algorithms for autonomous systems by proposing a Cycle-of-Learning framework that integrates human interaction modalities like demonstration, intervention, and evaluation, with results including a taxonomy and defined switching criteria.
We discuss different types of human-robot interaction paradigms in the context of training end-to-end reinforcement learning algorithms. We provide a taxonomy to categorize the types of human interaction and present our Cycle-of-Learning framework for autonomous systems that combines different human-interaction modalities with reinforcement learning. Two key concepts provided by our Cycle-of-Learning framework are how it handles the integration of the different human-interaction modalities (demonstration, intervention, and evaluation) and how to define the switching criteria between them.