マルコフ決定過程における TD 法による学習アルゴリズムについて(最適化問題における確率モデルの展開と応用)
スポンサーリンク
概要
著者
関連論文
- 未知の推移確率行列の事前・事後区間表現とマルコフ決定過程について (不確実・不確定性下での意思決定過程)
- 不確実性の下でのマルコフ決定過程に対する区間ベイズ手法 (不確実性と意思決定の数理)
- マルコフ決定過程のおける適応型アルゴリズム
- マルコフ決定過程における TD 法による学習アルゴリズムについて(最適化問題における確率モデルの展開と応用)
- 最適値関数に表れる黄金比(最適化問題における確率モデルの展開と応用)
- Dynamic Programming creates The Golden Ratio, too(Mathematical Models and Decision Making under Uncertainty)
- 区間ベイズ推定による適応型品質管理 (不確実な状況における意思決定の理論と応用)
- ダイナミックプログラミングを用いたファジィメトリッククラスタリング (非加法性の数理と情報 : 非加法性と凸解析)
- A pattern-matrix learning algorithm for adaptive MDPs : The regularly communicating case (Theory and Application of Decision Analysis in Uncertain Situation)
- A modified pattern matrix algorithm for multichain MDPs(The Development of Information and Decision Processes)
- A learning algorithm for communicating Markov decision processes with unknown transition matrices(Mathematical Models and Decision Making under Uncertainty)
- A structured pattern matrix algorithm for multichain Markov decision processes(Mathematics of Optimization : Methods and Practical Solutions)
- コンピュータの積極的活動を目指した学習指導の改善 : 第2次の研究
- Product possibility space with finitely many independent fuzzy vectors (非加法性の数理と情報:非加法性と凸解析--RIMS研究集会報告集)
- 1-B-9 「不確実性理論の経営科学への応用」研究部会終了報告(意思決定)
- Regret-optimal policies in absorbing semi-Markov decision processes with multiple constraints(The Development of Information and Decision Processes)
- Fuzzy Perceptive Values for MDPs with Discounting (Mathematical Theory and Applications of Uncertainty Sciences and Decision Making)
- Fuzzy perceptive values for stopping models and MDPs
- Dynamic Decision Making with Fuzzy Preferences as a Utility Function (不確実で動的なシステムへの最適化理論とその展開 短期共同研究報告集)
- Regret-Optimality Equation in Semi-MDP's with an Absorbing Set (Mathematical Programming Concerning Decision Makings and Uncertainties)
- Fuzzy Metric Clustering and Dynamic Programming
- A Dynamic Decision Making Model with an Objective Function based on Fuzzy Preferences
- A Discrete-Time Consumption and Wealth Model with Uncertainty
- A Fuzzy Stopping Problem with the Concept of Perception (Mathematics of Decision-making under uncertainty)
- ファジィ確率変数の最適化問題とファイナンスへの応用 (動的システム最適化理論の展開とその応用)
- 区間値およびファジー値をもつ行列ゲーム (動的システム最適化理論の展開とその応用)
- American Options with Uncertainty of the Stock Prices : The Discrete-Time Model (Mathematical Decision Making under Uncertainty)
- A note on interval games and their saddle points (Mathematical Optimization Theory and its Algorithm)
- コンピュータの積極的活用を目指した学習指導の改善
- Markov decision processes with fuzzy rewards (Perspective and problem for Dynamic Programming with uncertainty)
- On a Fuzzy Extension of Stopping Times (Perspective and problem for Dynamic Programming with uncertainty)
- Fuzzy Stopping in Continuous-Time Systems with Randomness and Fuzziness (Mathematical Modeling and Optimization under Uncertainty)
- A monotone convergence theorem for a sequence of convex fuzzy sets on $\mathbb{R}^n$ (Mathematical Science of Optimization)
- A fuzzy treatment of uncertain Markov decision processes : Average case (Mathematical Decision Making under uncertainty and ambiguity)
- A fuzzy treatment of uncertain Markov decision processes (Continuous and Discrete Mathematics for Optimization)
- Sequences of Fuzzy Sets on $\mathbb{R}^n$ (Decision Theory in Mathematical Modelling)
- ファジィ・システムにおける意思決定の展開(確率ファジィ解析とその周辺)
- Some Pseudo-Order of Fuzzy Sets on $\mathbb{R}^n$
- The Optimal Stopping Problem for Fuzzy Random Sequences (Decision Theory and Its Related Fields)
- 区間ベイズ手法による不適合品の事前検出 (不確実性下における意思決定問題)
- 停止マルコフ決定過程における制約条件付き最適化問題 (動的システム最適化理論の展開とその応用)
- Stopped Markov Decision Processes with Multiple Constraints (Perspective and problem for Dynamic Programming with uncertainty)
- Markov Decision Processes with a Constrained Stopping Time : Mathematical programming formulation (Mathematical Science of Optimization)
- ディンキンゲームとその多数回停止モデルへの拡張(最適タイミングの数理)
- ORDERING OF CONVEX FUZZY SETS : A BRIEF SURVEY AND NEW RESULTS
- 零加法性 Lusin 定理による Fuzzy neural network の近似について(非加法の数理と情報 : 函数解析の視点から)
- Further properties of null-additive fuzzy measure on metric spaces (Mathematical Theory and Applications of Uncertainty Sciences and Decision Making)
- Stopped Decision Processes with General Utility (Dynamic Decision Systems under Uncertain Environments)
- A utility deviation in discounted Markov decision processes with general utility
- DISCOUNTED MARKOV DECISION PROCESSES WITH GENERAL UTILITY FUNCTIONS(Optimization Theory and its Applications in Mathematical Systems)
- MDPにおける効用関数とモーメント最適性(確率モデル(1))
- Constrained Markov Decision Processes With Compact State And Action Sspaces : The Average Case (Dynamic Decision Systems under Uncertain Environments)
- Fuzzy Decision Processes with an Average Reward Criterion(Discrete and Continuous Structures in Optimization)
- Dynamic Fuzzy Systems with Time Average Rewards(Optimization Theory and its Applications in Mathematical Systems)
- Markov-Type Fuzzy Decision Processes with a Discounted Reward on a Closed Interval(Mathematical Structure of Optimization Theory)
- Multi-Variate Stopping Problem with a Monotone Logical Rule (決定過程論とその周辺)
- Controlled Markov Set-Chains Under Average Criteria (Decision Theory and Its Related Fields)
- Controlled Markov Set-Chains with Discounting(Optimization Methods for Mathematical Systems with Uncertainty)
- Constrained Markov Decision Processes : The Average Case(Mathematical Structure of Optimization Theory)
- 2-F-2 Multichain Markov decision processes and structured pattern matrix algorithm
- 2-D-6 研究グループ「不確実環境下での柔構造最適化モデリング」活動報告(柔構造最適化モデル)
- 区間ベイズ手法と逐次抜き取り問題について (不確実・不確定環境下における数理的意思決定とその周辺)
- 1-B-3 研究部会「確率最適化モデルとその応用」平成23年度活動中間報告(特別セッション 確率最適化モデルとその応用(1))