TY  - CONF
A1  - Kraus, Matthias
A1  - Wagner, Nicolas
A1  - Riekenbrauck, Ron
A1  - Minker, Wolfgang
T1  - Improving proactive dialog agents using socially-aware reinforcement learning
T2  - UMAP '23: Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization, Limassol, Cyprus, June 26-29, 2023
N2  - The next step for intelligent dialog agents is to escape their role as silent bystanders and become proactive. Well-defined proactive behavior may improve human-machine cooperation, as the agent takes a more active role during interaction and takes off responsibility from the user. However, proactivity is a double-edged sword because poorly executed pre-emptive actions may have a devastating effect not only on the task outcome but also on the relationship with the user. For designing adequate proactive dialog strategies, we propose a novel approach including both social as well as task-relevant features in the dialog. Here, the primary goal is to optimize proactive behavior so that it is task-oriented - this implies high task success and efficiency - while also being socially effective by fostering user trust. Including both aspects in the reward function for training a proactive dialog agent using reinforcement learning showed the benefit of our approach for more successful human-machine cooperation.
Y1  - 2023
UR  - https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/101335
SN  - 978-1-4503-9932-6
SP  - 146
EP  - 155
PB  - Association for Computing Machinery (ACM)
CY  - New York, NY
ER  -