AIHCROAug 28, 2018

Cycle-of-Learning for Autonomous Systems from Human Interaction

arXiv:1808.09572v220 citations
Originality Synthesis-oriented
AI Analysis

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes