 |
ML Newsnew | past | best | rss | submit | about |
| Robot Gains Social Intelligence Through Multimodal Deep Reinforcement Learning (arxiv.org) | |
| 2 points by JamilD on Mar 3, 2017 | hide | past | pdf | discuss on HN | |
|
In plain words: A robot learns social interaction skills by trial and error, taking in raw camera and sound signals and adjusting its actions from people's reactions instead of following hand-written rules. After 14 days of interacting with people, it had learned basic interaction skills. Abstract · Robot gains Social Intelligence through Multimodal Deep Reinforcement LearningFor robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills through a trial and error method. This paper aims to develop a robot that gathers data during its interaction with a human and learns human interaction behaviour from the high-dimensional sensory information using end-to-end reinforcement learning. This paper demonstrates that the robot was able to learn basic interaction skills successfully, after 14 days of interacting with people. | |
| add comment on HN |