Title
Learning to communicate proactively in human-agent teaming
Author
van Zoelen, E.M.
Cremers, A.H.M.
Dignum, F.P.M.
van Diggelen, J.
Peeters, M.M.
Contributor
De La Prieta, F. (editor)
Publication year
2020
Abstract
Artificially intelligent agents increasingly collaborate with humans in human-agent teams. Timely proactive sharing of relevant information within the team contributes to the overall team performance. This paper presents a machine learning approach to proactive communication in AI-agents using contextual factors. Proactive communication was learned in two consecutive experimental steps: (a) multi-agent team simulations to learn effective communicative behaviors, and (b) human-agent team experiments to refine communication suitable for a human team member. Results consist of proactive communication policies for communicating both beliefs and goals within human-agent teams. Agents learned to use minimal communication to improve team performance in simulation, while they learned more specific socially desirable behaviors in the human-agent team experiment. © Springer Nature Switzerland AG 2020.
Subject
BDI-agent
Context-sensitive
Human-agent communication
Human-agent teaming
Proactive
Reinforcement Learning
To reference this document use:
http://resolver.tudelft.nl/uuid:5cd890c9-bdf2-4442-86f4-6225cdf14983
DOI
https://doi.org/10.1007/978-3-030-51999-5_20
TNO identifier
878710
Publisher
Springer, Cham
ISBN
9783030519988
Source
18th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2020; L’Aquila; Italy; 7 October 2020 through 9 October 2020, 1233, 238-249
Series
Communications in Computer and Information Science
Document type
conference paper