X
Xin Xu
Researcher at National University of Defense Technology
Publications - 132
Citations - 5218
Xin Xu is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Reinforcement learning & Artificial neural network. The author has an hindex of 28, co-authored 109 publications receiving 3778 citations. Previous affiliations of Xin Xu include Huazhong University of Science and Technology.
Papers
More filters
Journal ArticleDOI
Data-Driven Intelligent Transportation Systems: A Survey
TL;DR: A survey on the development of D2ITS is provided, discussing the functionality of its key components and some deployment issues associated with D2 ITS Future research directions for the developed system are presented.
Journal ArticleDOI
Multi-view learning overview
TL;DR: This overview reviews theoretical underpinnings of multi-view learning and attempts to identify promising venues and point out some specific challenges which can hopefully promote further research in this rapidly developing field.
Journal ArticleDOI
Multiobjective Reinforcement Learning: A Comprehensive Overview
Chunming Liu,Xin Xu,Dewen Hu +2 more
TL;DR: The basic architecture, research topics, and naïve solutions of MORL are introduced at first and several representative MORL approaches and some important directions of recent research are comprehensively reviewed.
Journal ArticleDOI
Kernel-Based Least Squares Policy Iteration for Reinforcement Learning
Xin Xu,Dewen Hu,Xicheng Lu +2 more
TL;DR: The KLSPI algorithm provides a general RL method with generalization performance and convergence guarantee for large-scale Markov decision problems (MDPs) and can be applied to online learning control by incorporating an initial controller to ensure online performance.
Journal ArticleDOI
Incremental Learning From Stream Data
TL;DR: This paper proposes a general adaptive incremental learning framework named ADAIN that is capable of learning from continuous raw data, accumulating experience over time, and using such knowledge to improve future learning and prediction performance.