Improvement for action strategy learning in classification task using classification probalilities

Chyon Hae Kim, Shota Yamazaki, Hiroshi Tsujino, Shigeki Sugano

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, we address the autonomous evidence accumulation when a system classifies an object into one of predetermined categories. We propose a reinforcement learning system that effectively selects actions to speed up the classification process. The proposed system accelerates its learning using classification probabilities calculated by a classification system. We conducted three binary classification experiments to evaluate the learning speed and correctness of the proposed system. In the first experiment, we examined a random action selection strategy that does not learn its selection parameters while accumulating evidence. In the second experiment, we examined Paletta's reinforcement learning system that observes the state of the object and learns action selection strategy. In the third experiment, we examined the proposed system that observes both the object state and the classification probability. The proposed system showed the fastest learning.

Original languageEnglish
Title of host publication6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012
Pages352-358
Number of pages7
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 Joint 6th International Conference on Soft Computing and Intelligent Systems, SCIS 2012 and 13th International Symposium on Advanced Intelligence Systems, ISIS 2012 - Kobe, Japan
Duration: 2012 Nov 202012 Nov 24

Publication series

Name6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012

Other

Other2012 Joint 6th International Conference on Soft Computing and Intelligent Systems, SCIS 2012 and 13th International Symposium on Advanced Intelligence Systems, ISIS 2012
CountryJapan
CityKobe
Period12/11/2012/11/24

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint Dive into the research topics of 'Improvement for action strategy learning in classification task using classification probalilities'. Together they form a unique fingerprint.

  • Cite this

    Kim, C. H., Yamazaki, S., Tsujino, H., & Sugano, S. (2012). Improvement for action strategy learning in classification task using classification probalilities. In 6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012 (pp. 352-358). [6505012] (6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012). https://doi.org/10.1109/SCIS-ISIS.2012.6505012