Abstract
In this paper, we propose a novel learning method for the combined knowledge acquisition model. The combined knowledge acquisition model is a model for knowledge acquisition in which an agent heuristically find new knowledge by integrating existing plural knowledge. In the conventional model, there are two separate phases for combined knowledge acquisition: (a) solving a task with existing knowledge by trial and error and (b) learning new knowledge based on the experience in solving the task. However, since these two phases are carried out serially, the efficiency of learning was poor. In this paper, in order to improve this problem, we propose a novel knowledge acquisition method which realizes two phases simultaneously. Computer simulation results show that the proposed method much improves the efficiency of learning new knowledge.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yabe, T., Hattori, M.: Combined knowledge acquisition model by integration of existing knowledge (in Japanese). In: Proceedings of Forum on Information Technology, H-005, pp. 399–400 (2006)
Yabe, T., Hattori, M.: Research on characteristic and real environment applicability of combined knowledge acquisition model by integration of knowledge. In: Proceedings of 70th National Convention of Information Processing Society of Japan, 5V–6, 2, pp. 283–284 (2008)
Shikina, S., Hattori, M.: Learning for selection of existing knowledge in combined tasks (in Japanese). In: Proceedings of 72th National Convention of Information Processing Society of Japan, 2U–8, 2, pp. 239–340 (2010)
Shibata, K., Iida, M.: Acquisition of box pushing by direct-vision-based reinforcement learning. In: SICE 2003 Annual Conference, vol. 3, pp. 2322–2327 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Henmi, K., Hattori, M. (2016). Parallel Learning for Combined Knowledge Acquisition Model. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9947. Springer, Cham. https://doi.org/10.1007/978-3-319-46687-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-46687-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46686-6
Online ISBN: 978-3-319-46687-3
eBook Packages: Computer ScienceComputer Science (R0)