年単位の研究成果
フィンガープリント Harukazu Igarashiが有効な場合、研究トピックを掘り下げます。このトピックラベルは、この人物の業績からのものです。これらはともに一意のフィンガープリントを構成します。
ネットワーク
最近の国レベルでの外部協力。点をクリックして詳細を開いてください。
研究成果
Policy gradient reinforcement learning with separated knowledge: Environmental dynamics and action-values in policies
Ishihara, S. & Igarashi, H., 2016, ： : IEEJ Transactions on Electronics, Information and Systems. 136, 3, p. 282-289 8 p.研究成果: Article
Policy gradient method using fuzzy controller in policies and its application
Noor Imanina, N. H. & Igarashi, H., 2014, International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2014, Held at the 3rd World Congress on Computing and Information Technology, WCIT. Society of Digital Information and Wireless Communications (SDIWC), p. 167-174 8 p.研究成果: Conference contribution
Agent Control in Multiagent Systems: Reinforcement Learning of Weight Parameters in Particle Swarm Optimization
Igarashi, H., H, M., a, A., Ishihara, S. & Sasano, I., 2012 3 31, ： : The research reports of Shibaura Institute of Technology -- Natural Sciences and Engineering. 56, p. 1-8研究成果: Article
Learning of Soccer Player Agents Using a Policy Gradient Method : Coordination between Kicker and Receiver during Free Kicks
Igarashi, H. & Ishihara, H. IKS., 2011 4 4, ： : International Journal of Artificial Intelligence and Expert Systems. 2, p. 123-135研究成果: Article
Policy gradient approach for learning of soccer player agents: Pass selection of midfielders
Igarashi, H., Fukuoka, H. & Ishihara, S., 2011 1 10, Intelligent Control and Computer Engineering. p. 137-148 12 p. (Lecture Notes in Electrical Engineering; 巻数 70 LNEE).研究成果: Conference contribution