Masami Yasuda

Learn More
In this paper, we consider the model that the information on the rewards in vector-valued Markov decision processes includes imprecision or ambiguity. The fuzzy reward model is analyzed as follows: The fuzzy reward is represented by the fuzzy set on the multi-dimensional Euclidian space R and the infinite horizon fuzzy expected discounted reward(FEDR) from(More)
In this paper, the well-known Egoroff’s theorem in classical measure theory is established on monotone non-additive measure spaces. Taylor’s theorem, which concerns almost everywhere convergence of measurable function sequence in classical measure theory, is also generalized. The converse problem of the theorems are discussed, and a necessary and sufficient(More)
7 In this paper, we show that weakly null-additive fuzzy measures on metric spaces possess regularity. Lusin’s theorem, which is well-known in classical measure theory, is generalized to fuzzy measure space by using the 9 regularity and weakly null-additivity. A version of Egoro2’s theorem for the fuzzy measure de3ned on metric spaces is given. An(More)
This study is concerned with finite Markov decision processes (MDPs) whose state are exactly observable but its transition matrix is unknown. We develop a learning algorithm of the reward-penalty type for the communicating case of multi-chain MDPs. An adaptively optimal policy and an asymptotic sequence of adaptive policies with nearly optimal properties(More)
We shall discuss further regularity properties of null-additive fuzzy measure on metric spaces following the previous results. Under the null-additivity condition, some properties of the inner/outer regularity and the regularity of fuzzy measure are shown. Also the strong regularity of fuzzy measure is discussed on complete separable metric spaces. As an(More)
The optimization problem of general utility case is considered for countable state semi-Markov decision processes. The regret-utility function is introduced as a function of two variables, one is a target value and the other is a present value. We consider the expectation of the regret-utility function incured until the reaching time to a given absorbing(More)