M
Masa-aki Sato
Publications - 21
Citations - 935
Masa-aki Sato is an academic researcher. The author has contributed to research in topics: Reinforcement learning & Chaotic. The author has an hindex of 8, co-authored 21 publications receiving 894 citations.
Papers
More filters
Journal ArticleDOI
Online Model Selection Based on the Variational Bayes
TL;DR: By combining sequential model selection procedures, the online VB method provides a fully online learning method with a model selection mechanism and was able to adapt the model structure to dynamic environments.
Journal ArticleDOI
On-line EM Algorithm for the Normalized Gaussian Network
Masa-aki Sato,Shin Ishii +1 more
TL;DR: It is shown that the on-line EM algorithm is equivalent to the batch EM algorithm if a specific scheduling of the discount factor is employed and can be considered as a stochastic approximation method to find the maximum likelihood estimator.
Book ChapterDOI
Reinforcement Learning for Biped Locomotion
TL;DR: This paper proposes a new RL method for central pattern generators that generates stable rhythmic movements such as biped locomotion called the CPG-actir-critic method, and applies this method to the RL for the biped robot.
Journal ArticleDOI
Associative memory based on parametrically coupled chaotic elements
Shin Ishii,Masa-aki Sato +1 more
TL;DR: An associative memory system based on parametrically coupled chaotic elements that makes an efficient association over the memories that are stored by means of autocorrelational learning is proposed.
Journal ArticleDOI
Chaotic Potts spin model for combinatorial optimization problems
Shin Ishii,Masa-aki Sato +1 more
TL;DR: Some of the bifurcation properties of Potts mean-field-theory annealing applied to traveling salesman problems are shown and a nonequilibrium version of the Potts spin neural network, called chaotic Pottsspin (CPS), is proposed.