Intrinsically motivated reinforcement learning for human–robot interaction in the real-world

• Published in: Neural networks Vol. 107; pp. 23 - 33
• Main Authors: Qureshi, Ahmed Hussain, Nakamura, Yutaka, Yoshikawa, Yuichiro, Ishiguro, Hiroshi
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2018
• Subjects: Deep Learning; Deep reinforcement learning; Humans; Human–robot interaction; Intrinsic motivation; Neural Networks (Computer); Real-world robotics; Robotics - methods; Social robots; Social Skills; User-Computer Interface; Intrinsic motivation; Deep reinforcement learning; Real-world robotics; Human–robot interaction; Social robots
• ISSN: 0893-6080; 1879-2782
• DOI: 10.1016/j.neunet.2018.03.014

For a natural social human–robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human–robot interaction experiences gathered in the real uncontrolled environments. The results indicate that the robot not only acquired human-like social skills but also took more human-like decisions, on a test dataset, than a robot which received direct rewards for the task achievement.