Research topics
Learning in Game-theoretic Situations †
拡張された情報理論(多変量双方向情報理論 (Hidaka, 2012))に基づく概念モデル形成過程のモデル化 †
【キーワード】知識獲得，仮説生成，情報理論，非線形力学系，時系列解析
- Pub2014LearningInGames 鳥居 拓馬, 日高 昇平, 真隅 暁 (2014). 学習あり繰り返し囚人のジレンマにおける協調行動の発生., 第28回人工知能学会全国大会, 4H1-3. [Publications]
- Pub2014MethodologicalImprovementLearningInGamesUoU Hidaka, S., T. Torii, & A. Masumi (2014). Tractable Infinite Order Markov Analysis for Iterated Games with Learners., In Proceedings of the Joint 7th International Conference on Soft Computing and Intelligent Systems and 15th International Symposium on Advanced Intelligent Systems, 286-291, ISBN: 978-1-4799-5954-9. ((SCIS & ISIS 2014) held on December 3rd-6th, Kitakyushu International Conference Center, Kitakyushu, Japan.) [Publications]
- Pub2015LearningInGames 鳥居拓馬 & 日高昇平 (2015). 利己的な相互協調：強化学習主体による不確実な囚人のジレンマ. 第29回人工知能学会全国大会, 1L5-3. (link) [Publications]
- Pub2015LearningInGamesUoU 鳥居拓馬 & 日高昇平 (2015). 利己的な学習による相互協調：不確実な囚人のジレンマの分析., 認知科学, 22(3), 341-355. (url) In English: Torii, T. & Hidaka, S. (2015). Mutual Cooperation Out of Greedy Learners: Prisoner's Dilemma Under Uncertainty., Cognitive Studies, 22(3) 341-355. [Publications]
- PubSelected?PreprintPub2015LearningInGamesUoU Hidaka, S. (2015). Recursive Markov Process., eprint arXiv:1509.00535.(link) [Publications]
- PubSelected?Pub2015LearningInGamesUoU Hidaka, S., Torii, T. & Masumi, A. (2015). Which types of learning make a simple game complex?, Complex Systems, 24(1), 49--74. (link) [Publications]
![[PukiWiki]](image/pukiwiki.png "[PukiWiki]")
