Many Episode Learning in a Modular Embodied Agent via End-to-End Interaction

04/19/2022
by   Yuxuan Sun, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 8

page 14

page 15

page 16

page 17

page 18

research
09/08/2016

Ashwin: Plug-and-Play System for Machine-Human Image Annotation

We present an end-to-end machine-human image annotation system where eac...
research
10/17/2022

Multi-Agent Automated Machine Learning

In this paper, we propose multi-agent automated machine learning (MA2ML)...
research
11/13/2020

End-to-End Learning from Noisy Crowd to Supervised Machine Learning Models

Labeling real-world datasets is time consuming but indispensable for sup...
research
04/25/2023

VeML: An End-to-End Machine Learning Lifecycle for Large-scale and High-dimensional Data

An end-to-end machine learning (ML) lifecycle consists of many iterative...
research
01/27/2019

Modularization of End-to-End Learning: Case Study in Arcade Games

Complex environments and tasks pose a difficult problem for holistic end...
research
04/26/2017

Limits of End-to-End Learning

End-to-end learning refers to training a possibly complex learning syste...
research
03/29/2020

Dealer: End-to-End Data Marketplace with Model-based Pricing

Data-driven machine learning (ML) has witnessed great successes across a...

Please sign up or login with your details

Forgot password? Click here to reset