Looking Back and Ahead: Adaptation and Planning by Gradient Descent

Shingo Murata, Hiroki Sawa, Shigeki Sugano, Tetsuya Ogata

研究成果: Conference contribution

抜粋

Adaptation and planning are crucial for both biological and artificial agents. In this study, we treat these as an inference problem that we solve using a gradient-based optimization approach. We propose adaptation and planning by gradient descent (APGraDe), a gradient-based computational framework with a hierarchical recurrent neural network (RNN) for adaptation and planning. This framework computes (counterfactual) prediction errors by looking back on past situations based on actual observations and by looking ahead to future situations based on preferred observations (or goal). The internal state of the higher level of the RNN is optimized in the direction of minimizing these errors. The errors for the past contribute to the adaptation while errors for the future contribute to the planning. The proposed APGraDe framework is implemented in a humanoid robot and the robot performs a ball manipulation task with a human experimenter. Experimental results show that given a particular preference, the robot can adapt to unexpected situations while pursuing its own preference through the planning of future actions.

元の言語English
ホスト出版物のタイトル2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019
編集者Amir Aly, Estela Bicho, Sofiane Boucenna, Bruno Castro da Silva, Mohamed Chetouani, Angel P. del Pobil, Julien Diard, Stephane Doncieux, Tilbe Goksun, Angela Grimminger, Frank Guerin, Yoshinobu Hagiwara, Lorenzo Jamone, Sinan Kalkan, Bruno Lara, Clement Moulin-Frier, Shingo Murata, Takayuki Nagai, Yukie Nagai, Iris Nomikou, Masaki Ogino, Pierre-Yves Oudeyer, Alfredo F. Pereira, Alexandre Pitti, Joanna Raczaszek-Leonardi, Sebastian Risi, Benjamin Rosman, Yulia Sandamirskaya, Malte Schilling, Alessandra Sciutti, Patricia Shaw, Andrea Soltoggio, Michael Spranger, Tadahiro Taniguchi, Serge Thill, Jochen Triesch, Emre Ugur, Anna-Lisa Vollmer
出版者Institute of Electrical and Electronics Engineers Inc.
ページ151-156
ページ数6
ISBN(電子版)9781538681282
DOI
出版物ステータスPublished - 2019 8
イベント9th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019 - Oslo, Norway
継続期間: 2019 8 192019 8 22

出版物シリーズ

名前2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019

Conference

Conference9th Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019
Norway
Oslo
期間19/8/1919/8/22

    フィンガープリント

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Control and Optimization

これを引用

Murata, S., Sawa, H., Sugano, S., & Ogata, T. (2019). Looking Back and Ahead: Adaptation and Planning by Gradient Descent. : A. Aly, E. Bicho, S. Boucenna, B. Castro da Silva, M. Chetouani, A. P. del Pobil, J. Diard, S. Doncieux, T. Goksun, A. Grimminger, F. Guerin, Y. Hagiwara, L. Jamone, S. Kalkan, B. Lara, C. Moulin-Frier, S. Murata, T. Nagai, Y. Nagai, I. Nomikou, M. Ogino, P-Y. Oudeyer, A. F. Pereira, A. Pitti, J. Raczaszek-Leonardi, S. Risi, B. Rosman, Y. Sandamirskaya, M. Schilling, A. Sciutti, P. Shaw, A. Soltoggio, M. Spranger, T. Taniguchi, S. Thill, J. Triesch, E. Ugur, ... A-L. Vollmer (版), 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019 (pp. 151-156). [8850693] (2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DEVLRN.2019.8850693