Takato Tatsumi

Research map »

 

Research field

Learning classifier system: evolutionary computation and reinforcement learning

Papers

Journals

  • Takato Tatusmi, Takahiro Komine, Masaya Nakata, Hiroyuki Sato, and Keiki Takadama:

    “A Learning Classifier System that Adapts Accuracy Criterion”,
    Transaction of the Japanese Society for Evolutionary Computation Vol. 6 (2015) No. 2 p. 90-103Download »

  • Kazuma Matsumoto, Takato Tatsumi, Hiroyuki Sato, Tim Kovacs, and Keiki Takadama:

    “XCSR Learning from Compressed Data Acquired by Deep Neural Network”,
    Journal of Advanced Computational Intelligence and Intelligent Informatics Vol.21 No.5 pp. 856-867Download »

  • Caili Zhang, Takato Tatsumi, Masaya Nakata, and Keiki Takadama:

    “Approach to Clustering with Variance-Based XCS”,
    Journal of Advanced Computational Intelligence and Intelligent Informatics Vol.21 No.5 pp. 885-894Download »

  • Takato Tatsumi, Hiroyuki Sato, and Keiki Takadama:

    “Learning Classifier System Based on Mean of Reward”,
    Journal of Advanced Computational Intelligence and Intelligent Informatics Vol.21 No.5 pp. 895-906Download »

  • Takato Okudo, Tomohiro Yamaguchi, Akinori Murata, Takato Tatsumi, Fumito Uwano, and Keiki Takadama:

    “Supporting the Exploration of the Learning Goals for a Continuous Learner Toward Creative Learning”,
    Journal of Advanced Computational Intelligence and Intelligent Informatics Vol.21 No.5 pp. 907-916Download »

  • Conferences

  • Takato Tatsumi, Takahiro Komine, Hiroyuki Sato, Keiki Takadama:

    “Handling Different Level of Unstable Reward Environment Through an Estimation of Reward Distribution in XCS”,
    IEEE Congress on Evolutionary Computation (CEC) 2015 pp. 2973-2980, May 25-28, 2015, Sendai, Japan.Download »

  • Takato Tatsumi, Takahiro Komine, Masaya Nakata, Hiroyuki Sato, Tim Kovacs, Keiki Takadama:

    “Variance-based Learning Classifier System without Convergence of Reward Estimation”,
    Genetic and Evolutionary Computation Conference (GECCO) pp. 67-68, July 2016, Denver, USA.Download »

  • Caili Zhang, Takato Tatsumi, Masaya Nakata, Keiki Takadama, Hiroyuki Sato, Tim Kovacs:

    “Extracting Different Abstracted Level Rule with Variance-Based LCS”,
    2016 Joint 8th International Conference on Soft Computing and Intelligent Systems (SCIS) and 17th International Symposium on Advanced Intelligent Systems (ISIS) pp. 160-165, August 2016, Hokkaido, Japan.Download »

  • Haruyuki Ishii, Keiki Takadama, Akinori Murata, Fumito Uwano, Takato Tatsumi, Yuta Umenai, Kazuma Matsumoto, Hiroyuki Kamata, Takayuki Ishida, Seisuke Fukuda, Shujiro Sakai, Shinichiro Sawai:

    “The Robust Spacecraft Location Estimation Algorithm Toward The Misdetection Crater and The Undetected Crater in SLIM”,
    The 31th International Symposium on Space Technology and Science (ISTS2017), July 2017, Ehime, Japan.

  • Takato Tatsumi, Hiroyuki Sato, Tim Kovacs, Keiki Takadama:

    “Applying Variance-based Learning Classifier System without Convergence of Reward Estimation into Various Reward Distribution”,
    IEEE Congress on Evolutionary Computation (CEC) pp. 2630-2637, June 2017, Donostia, Spain.Download »

  • Takato Tatsumi, Hiroyuki Sato, Keiki Takadama:

    “Automatic Adjustment of Selection Pressure based on Range of Reward in Learning Classifier System”,
    Genetic and Evolutionary Computation Conference (GECCO) pp. 505-512, July 2017, Berlin, Germany.Download »

  • Fumito Uwano, Haruyuki Ishii, Yuta Umenai, Kazuma Matsumoto, Takato Tatsumi, Akinori Murata, Keiki Takadama:

    “Analyzing Triangle Matching Method Based on Craters for Spacecraft Localization”,
    The 14th International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS2018), June 2018, Madrid, Spain.

  • Haruyuki Ishii, Yuta Umenai, Kazuma Matsumoto, Fumito Uwano, Takato Tatsumi, Keiki Takadama, H. Kamata, T. Ishida, S. Fukuda, S. Sawai, S. Sakai:

    “How to Detect Essential Craters in Camera Shot Image for
    Increasing the Number of Spacecraft Location Candidates while Improving Its Estimation Accuracy?”,
    The 14th International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS2018), June 2018, Madrid, Spain.

  • Takato Tatsumi, Tim Kovacs, Keiki Takadama:

    “XCS-CR: Determining Accuracy of Classifier by its Collective Reward in Action Set toward Environment with Action Noise”,
    International Workshop on Learning Classifier Systems in Genetic and Evolutioary Computation Conference (GECCO) pp. 1457-1464, July 2018, Kyoto, Japan.Download »

  • Kazuma Matsumoto, Ryo Takano, Takato Tatsumi, Hiroyuki Sato, Tim Kovacs, Keiki Takadama:

    “XCSR based on compressed input by deep neural network for high dimensional data”,
    International Workshop on Learning Classifier Systems in Genetic and Evolutioary Computation Conference (GECCO) pp. 1418-1425, July 2018, Kyoto, Japan.Download »

  • Caili Zhang, Takato Tatsumi, Hiroyuki Sato, Tim Kovacs, Keiki Takadama:

    “Classifier generalization for comprehensive classifiers subsumption in XCS”,
    Evolutionary Computation in Health care and Nursing System in Genetic and Evolutioary Computation Conference (GECCO) pp. 1854-1861, July 2018, Kyoto, Japan.Download »

  •  

    Awards

  • Genetic and Evolutionary Computation Conference 2016 GECCO Student Travel Grant
  • The siciety of Instrument and Control Engineers SSI2017 SSI Excellent Paper Award