2 papers
math.PR2021
Path-dependent Poisson random measures and stochastic integrals constructed from general point processes
Konatsu Miyamoto
In this paper, we consider an extension of the Poisson random measure for the formulation of continuous-time reinforcement learning, such that both the frequency and the width of t…
math.OC2020
Convergence of Q-value in case of Gaussian rewards
Konatsu Miyamoto, Masaya Suzuki, Yuma Kigami +1
In this paper, as a study of reinforcement learning, we converge the Q function to unbounded rewards such as Gaussian distribution. From the central limit theorem, in some real-wor…