Shiyuan Wu

Shiyuan Wu

Auto-generated profile, based on publicly available information

Shiyuan Wu

School of Life Sciences, Shanghai University, Shanghai, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 February 2022 in Biological Control
Verified
Journal Article
Closed access
CZChao-Ying Zhen
Chao-Ying Zhen
WLWei-Dan Li
Wei-Dan Li
SWShi-Yuan Wu
Shi-Yuan Wu
PZPeng-Yu Zhao
Peng-Yu Zhao
Zhen QinZhen Qin
Zhen Qin
HGHai-yan Gao
Hai-yan Gao

1 January 2017 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
SCShou Chen
Shou Chen
SWShiyuan Wu
Shiyuan Wu
CMChao Mao
Chao Mao
BLBoya Li
Boya Li
Imitating the positioning rules in the bird flocking system, the strategic adjustment capacity is decomposed into three aspects, which are the organizational learning capacity from the top firms, the extent to which firms maintain or rely on the best operational capacity vector in history, and the ability to overcome the disadvantage while maintaining the advantage of the operational capacity vector from the previous years, respectively. Financial vectors are constructed to represent the results of corporate strategic adjustment and listed firms in the China A stock are chosen as the samples. As empirical analysis reveals, there is a positive correlation between the organizational learning capacity from the top firms and the firm performance and a U‐shaped relation between the learning capability from the previous best operational capacity vector and the firm performance. However, no significant correlation between the inertia control ability of the current operational capacity vector of the firms and their performance improvement can be observed. This study verifies that the issue of corporate competitiveness and performance can be investigated by utilizing the principles of competition in nature. Moreover, a firm can obtain a sustainable competitive advantage by improving its ability to learn from top firms in the industry.

6 November 2020
Verified
Conference Paper
Closed access
JHJunmin Hu
Junmin Hu
FZFengyi Zhao
Fengyi Zhao
JMJun Meng
Jun Meng
SWShiyuan Wu
Shiyuan Wu
Deep reinforcement learning is one of the core technologies, which leads to artificial intelligence. It has been used widely not only in robot, autonomous driving, power station control and human-computer interaction in mobile e-commerce platforms, but also in gambling games. The game software AlphaGo of artificial intelligence defeated Ke Jie in 2017. Since then, the study of artificial intelligence and deep reinforcement is widely concerned. We build a Neural Network model using TensorFlow and Monte Carlo tree search algorithm, so that agents can reach the level of playing chess with human beings in board games. The gobang interface is realized by Python, and the PhoenixGo recurrence is completed. The computation is reduced and the training effect of the agent is improved by optimizing the establishment of gobang strategic value network. Black hand first can achieve a 73% winning rate, and white hand first is 64%, when playing against human players.