2023 · 12 citations · 26 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningSocial BehaviorConversational InterfacesConversational User InterfacesDialogue SystemsReinforcement LearningReward DesignConversational AgentsDialog SystemsHuman-agent InteractionHuman-machine CollaborationReward Function DesignTask-oriented DialogueTask-oriented Dialogue SystemsUser Trust
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 on the task outcome and the relationship with the user. For designing adequate proactive dialog strategies, we propose a novel approach including both social and 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.
26
Reinforcement Learning: An Introduction
Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations
Principles of mixed-initiative user interfaces
Eric Horvitz · 1999 · 1.4K citations