Technical Note: \cal Q-Learning
Machine Learning
Purposive behavior acquisition for a real robot by vision-based reinforcement learning
Machine Learning - Special issue on robot learning
Learning the meaning of action commands based on "no news is good news" criterion
Proceedings of the 2007 workshop on Multimodal interfaces in semantic interaction
Hi-index | 0.00 |
In recent years, robots began to appear in our daily lives. However, people get bored with them after a short time. We therefore consider that robots that contact with people must have an ability to learn new actions, so that people enjoy the interaction for a long time. However, it is difficult for them to learn complex actions like games through human-robot interaction. If humans learn through human-human interaction, it is known that scaffolding is effective. Scaffolding is a method of promoting learning by gradually giving difficult learning tasks according to the ability of learners. If robots learn through human-robot interaction, it is possible that scaffolding also supports their learning. However, it has not clarified that scaffolding occurs actually through interactions with ordinary people in everyday situations. In this experiment, we clarify this problem, and propose the method of utilizing the scaffold given by ordinary people in everyday situations for robots that contact with people.