6 citations · 9 across the 2 of their papers we have counts for
2 papers
cs.AI2016★ 6 cited
On Reward Function for Survival
Naoto Yoshida
Obtaining a survival strategy (policy) is one of the fundamental problems of biological agents. In this paper, we generalize the formulation of previous research related to the sur…
cs.NE2015★ 3 cited
Q-Networks for Binary Vector Actions
Naoto Yoshida
In this paper reinforcement learning with binary vector actions was investigated. We suggest an effective architecture of the neural networks for approximating an action-value func…