Hui Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hui Zhang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Ya Zhang
School of Automation Southeast University Nanjing China
2 shared publications- Ya Zhang
School of Automation, Southeast University, Nanjing, China
2 shared publications - Changyin Sun
Southeast University, Nanjing, China
1 shared publication Hongfei Du
School of Mathematical Sciences University of Electronic Science and Technology of China Chengdu China
1 shared publicationJiachen Fu
School of Automation Southeast University Nanjing China
1 shared publicationJin Yu
1 shared publication
Latest Publications
- 1 February 2025
- Published by American Society of Civil Engineers (ASCE) in Journal of Transportation Engineering, Part A: Systems
- Vol. 151 (2)
Traffic Signal and Autonomous Vehicle Control Model: An Integrated Control Model for Connected Autonomous Vehicles at Traffic-Conflicting Intersections Based on Deep Reinforcement Learning
- 1 February 2025
- Published by American Society of Civil Engineers (ASCE) in Journal of Transportation Engineering, Part A: Systems
- Vol. 151 (2)
Traffic Signal and Autonomous Vehicle Control Model: An Integrated Control Model for Connected Autonomous Vehicles at Traffic-Conflicting Intersections Based on Deep Reinforcement Learning
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Control Theory & Applications
- Vol. 19 (1)
Multi‐Agent Reinforcement Learning Algorithm Based on Local Observation Imitation Learning
This paper investigates the error accumulation problem in centralized training and decentralized execution (CTDE) policy‐based multi‐agent reinforcement learning (MARL) algorithms, which arises from local observation inaccuracies. To address this issue, we propose a novel MARL algorithm that incorporates imitation learning using local observations. Firstly, by analysing the multi‐agent proximal policy optimization algorithm and examining the problems arising when global states are replaced with local observations, it is proved that insufficient observations can lead to information loss, thereby introducing errors of advantage function, and it is demonstrated that the generalized advantage estimation method accumulates errors during the training process. Then, imitation learning is introduced and a novel training framework that combines reinforcement learning and imitation learning is proposed. During the reinforcement learning phase, an MARL agent trained with global observations acts as an expert. Subsequently, imitation learning is applied to train another agent that mimics the expert's decisions using only local observations. Finally, the effectiveness of this algorithm is verified in some commonly used multi‐agent environments, which demonstrates its superior performance compared to traditional multi‐agent reinforcement learning algorithms.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Control Theory & Applications
- Vol. 19 (1)
Open AccessMulti‐Agent Reinforcement Learning Algorithm Based on Local Observation Imitation Learning
This paper investigates the error accumulation problem in centralized training and decentralized execution (CTDE) policy‐based multi‐agent reinforcement learning (MARL) algorithms, which arises from local observation inaccuracies. To address this issue, we propose a novel MARL algorithm that incorporates imitation learning using local observations. Firstly, by analysing the multi‐agent proximal policy optimization algorithm and examining the problems arising when global states are replaced with local observations, it is proved that insufficient observations can lead to information loss, thereby introducing errors of advantage function, and it is demonstrated that the generalized advantage estimation method accumulates errors during the training process. Then, imitation learning is introduced and a novel training framework that combines reinforcement learning and imitation learning is proposed. During the reinforcement learning phase, an MARL agent trained with global observations acts as an expert. Subsequently, imitation learning is applied to train another agent that mimics the expert's decisions using only local observations. Finally, the effectiveness of this algorithm is verified in some commonly used multi‐agent environments, which demonstrates its superior performance compared to traditional multi‐agent reinforcement learning algorithms.
- 13 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 53 (11) , 7115-7125
False Data-Injection Attack Detection in Cyber–Physical Systems With Unknown Parameters: A Deep Reinforcement Learning Approach
This article studies the detection of discontinuous false data-injection (FDI) attacks on cyber–physical systems (CPSs). Considering the unknown stochastic properties of the process noise and measurement noise, deep reinforcement learning is applied to designing an FDI attack detector. First, the discontinuous attack detection problem is modeled as a partially observable Markov decision process (POMDP) and a neural network is used to explore the POMDP. In the network, sliding observation windows which are composed of the offline fragment historical data are used as the input. An approach to designing the reward in POMDP is provided to ensure the precision of the detection when there are even some state recognition errors. Second, sufficient conditions on attack frequency and duration to guarantee the applicability of the detector and the expected estimation performance are further given. Finally, simulation examples illustrate the effectiveness of the attack detector.
- 13 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 53 (11) , 7115-7125
False Data-Injection Attack Detection in Cyber–Physical Systems With Unknown Parameters: A Deep Reinforcement Learning Approach
This article studies the detection of discontinuous false data-injection (FDI) attacks on cyber–physical systems (CPSs). Considering the unknown stochastic properties of the process noise and measurement noise, deep reinforcement learning is applied to designing an FDI attack detector. First, the discontinuous attack detection problem is modeled as a partially observable Markov decision process (POMDP) and a neural network is used to explore the POMDP. In the network, sliding observation windows which are composed of the offline fragment historical data are used as the input. An approach to designing the reward in POMDP is provided to ensure the precision of the detection when there are even some state recognition errors. Second, sufficient conditions on attack frequency and duration to guarantee the applicability of the detector and the expected estimation performance are further given. Finally, simulation examples illustrate the effectiveness of the attack detector.