In this work we give a case study of an embodied machine-learning (ML) powered agent that improves itself via interactions with crowd-workers. The agent consists of a set of modules, some of which are learned, and others heuristic. While the agent is not "end-to-end" in the ML sense, end-to-end interaction is a vital part of the agent's learning mechanism. We describe how the design of the agent works together with the design of multiple annotation interfaces to allow crowd-workers to assign credit to module errors from end-to-end interactions, and to label data for individual modules. Over multiple automated human-agent interaction, credit assignment, data annotation, and model re-training and re-deployment, rounds we demonstrate agent improvement.
@article{arxiv.2204.08687,
title = {Many Episode Learning in a Modular Embodied Agent via End-to-End Interaction},
author = {Yuxuan Sun and Ethan Carlson and Rebecca Qian and Kavya Srinet and Arthur Szlam},
journal= {arXiv preprint arXiv:2204.08687},
year = {2023}
}