1 code implementation • 6 Sep 2021 • Xingen Gao, Fei Chao, Changle Zhou, Zhen Ge, Chih-Min Lin, Longzhi Yang, Xiang Chang, Changjing Shang
On error of value function inevitably causes an overestimation phenomenon and has a negative impact on the convergence of the algorithms.
no code implementations • 1 Jan 2021 • Xingen Gao, Fei Chao, Changle Zhou, Zhen Ge, Chih-Min Lin, Longzhi Yang, Xiang Chang, Changjing Shang
In the reinforcement learning (RL) algorithms which incorporate function approximation methods, the approximation error of value function inevitably cause overestimation phenomenon and have a negative impact on the convergence of the algorithms.
1 code implementation • arXiv 2020 • Jialin Liu, Fei Chao, Chih-Min Lin
Data augmentation is one of the most effective approaches for improving the accuracy of modern machine learning models, and it is also indispensable to train a deep model for meta-learning.
1 code implementation • arXiv 2019 • Jialin Liu, Fei Chao, Longzhi Yang, Chih-Min Lin, Qiang Shen
This work proposes a method that controls the gradient descent process of the model parameters of a neural network by limiting the model parameters in a low-dimensional latent space.
no code implementations • 25 Sep 2019 • Jialin Liu, Fei Chao, Yu-Chen Lin, Chih-Min Lin
The results show that predicting stock price through price rate of change is better than predicting absolute prices directly.
no code implementations • 19 Sep 2019 • Jialin Liu, Chih-Min Lin, Fei Chao
Market economy closely connects aspects to all walks of life.