Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learning

TL;DR

This paper introduces a socially-aware reinforcement learning approach to improve proactive dialog agents, balancing task success and social trust to enhance human-machine cooperation.

Contribution

It proposes a novel reward function incorporating social and task features for training proactive dialog agents, improving cooperation.

Findings

Enhanced task success rates

Increased user trust and satisfaction

More socially effective proactive behavior

Abstract

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.