Nina Dethlefs
Papers
6
Total Citations
43
H-Index
4
About
Nina Dethlefs is a leading researcher at the intersection of machine learning, interactive systems, and robotics, with a particular focus on how machines can perceive, act, and communicate seamlessly with humans. Her work centers on developing scalable reinforcement learning (RL) frameworks for conversational agents and social robots, addressing the critical challenge of policy optimization in large, complex domains. Dethlefs has made major contributions through her pioneering work on nonstrict hierarchical reinforcement learning, which introduces flexible state transitions and linear function approximation to overcome scalability limitations in dialogue systems. Her research has been widely recognized, with her most-cited paper on machine learning for interactive systems and robots accumulating 16 citations, while her work on hierarchical dialogue policy learning and multimodal interaction has garnered significant attention in the field. Notably, she co-edited a special issue on machine learning for multiple modalities in interactive systems and robots, highlighting the importance of integrating speech, gestures, and vision. Dethlefs’s work bridges the gap between perception, action, and communication, advancing the development of more natural and effective human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1Machine learning for interactive systems and robots16 citations · 2013
- 2
- 3
- 4
- 5
- 6