Establishing Interaction between Machine and Medaka using Deep Q-Network
Journal Title: EAI Endorsed Transactions on Creative Technologies - Year 2016, Vol 3, Issue 9
Abstract
Social interaction is the basic ability for animals to survive. It is difficult for a machine to interact with human or other animals because it is not clear how the machine should interact. This paper examines whether an artificial dot controlled by a machine can interact with a medaka and induce a desired behavior. The dot is displayed on a monitor. We use deep Q network (DQN) to learn how to move the dot. As a result, the DQN could learn some basic elements to interact with the medaka and the desired behavior could be induced.
Authors and Affiliations
Ryo Nishimura, Hiroyuki Iizuka, Masahito Yamamoto
Keywords
Related Articles
- EP ID EP45860
- DOI http://dx.doi.org/10.4108/eai.3-12-2015.2262508
- Views 276
- Downloads 0
Varianish: Jamming with Pattern Repetition
In music, patterns and pattern repetition are often regarded as a machine-like task, indeed often delegated to drum Machines and sequencers. Nevertheless, human players add subtle differences and variations to repeated p...
Contextual Design of ICT for Physiotherapy: Toward Knowledge and Innovation Ecosystem
With advances in information and communication technologies (ICT), changes have been produced in physiotherapy provision. However, low adoption of the new technologies calls attention for better theoretical model and met...
Towards a novel and LMS-free Pervasive Learning System exploiting the Experience API
Experience API (xAPI), the evolution of SCORM (Sharable Content Object Reference Model) in e-learning content specifications, stably gains ground in education, defense and training. In this paper we shortly describe the...
Implementation of Human Cognitive Bias on Naïve Bayes
We propose a human-cognition inspired classification model based on Naïve Bayes. Our previous study showed that human-cognitively inspired heuristics is able to enhance the prediction accuracy of text classifier based on...
A Multimodal Interaction Framework for Blended Learning
Humans interact with each other by utilizing the five basic senses as input modalities, whereas sounds, gestures, facial expressions etc. are utilized as output modalities. Multimodal interaction is also used between hum...