Fangzhou Xiong

Fangzhou Xiong

Auto-generated profile, based on publicly available information

Fangzhou Xiong

State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Science, 100190, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), 100049, Beijing, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
19 February 2018 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
FXFangzhou Xiong
Fangzhou Xiong
BSBiao Sun
Biao Sun
Xu YangXu Yang
Xu Yang
HQHong Qiao
Hong Qiao
Kaizhu HuangKaizhu Huang
Kaizhu Huang
ZLZhiyong Liu
Zhiyong Liu
Policy search in reinforcement learning (RL) is a practical approach to interact directly with environments in parameter spaces, that often deal with dilemmas of local optima and real-time sample collection. A promising algorithm, known as guided policy search (GPS), is capable of handling the challenge of training samples using trajectory-centric methods. It can also provide asymptotic local convergence guarantees. However, in its current form, the GPS algorithm cannot operate in sequential multitask learning scenarios. This is due to its batch-style training requirement, where all training samples are collectively provided at the start of the learning process. The algorithm's adaptation is thus hindered for real-time applications, where training samples or tasks can arrive randomly. In this paper, the GPS approach is reformulated, by adapting a recently proposed, lifelong-learning method, and elastic weight consolidation. Specifically, Fisher information is incorporated to impart knowledge from previously learned tasks. The proposed algorithm, termed sequential multitask learning-GPS, is able to operate in sequential multitask learning settings and ensuring continuous policy learning, without catastrophic forgetting. Pendulum and robotic manipulation experiments demonstrate the new algorithms efficacy to learn control policies for handling sequentially arriving training samples, delivering comparable performance to the traditional, and batch-based GPS algorithm. In conclusion, the proposed algorithm is posited as a new benchmark for the real-time RL and robotics research community.

1 September 2020 in Neural Networks
Verified
Journal Article
Closed access
FXFangzhou Xiong
Fangzhou Xiong
ZLZhiyong Liu
Zhiyong Liu
Kaizhu HuangKaizhu Huang
Kaizhu Huang
XYXu Yang
Xu Yang
HQHong Qiao
Hong Qiao
AHAmir Hussain
Amir Hussain