Junbo Tong

Mr. Junbo Tong

Tsinghua University, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
28 July 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
XGXudong Guo
Xudong Guo
JTJunbo Tong
Junbo Tong
PCPeiyu Chen
Peiyu Chen
WFWenhui Fan
Wenhui Fan
The entire world has suffered a lot since the outbreak of the novel coronavirus (COVID-19) in 2019, so simulation models of COVID-19 dynamics are urgently needed to understand and control the pandemic better. Meanwhile, emotional contagion, the spread of vigilance or panic, serves as a negative feedback to the epidemic, but few existing models take it into consideration. In this study, we proposed an innovative multi-layer hybrid modelling and simulation approach to simulate disease transmission and emotional contagion together. In each layer, we used a hybrid simulation method combining agent-based modelling (ABM) with system dynamics modelling (SDM), keeping spatial heterogeneity while reducing computation costs. We designed a new emotion dynamics model IWAN (indifferent, worried, afraid and numb) to simulate emotional contagion inside a community during an epidemic. Our model was well fit to the data of China, the UK and the US during the COVID-19 pandemic. If there weren’t emotional contagion, our experiments showed that the confirmed cases would increase rapidly, for instance, the total confirmed cases during simulation in Guangzhou, China would grow from 334 to 2096, which increased by 528%. We compared the calibrated emotional contagion parameters of different countries and found that the suppression effect of emotional contagion in China is relatively more visible than that in the US and the UK. Due to the experiment results, the proposed multi-layer network model with hybrid simulation is valid and can be applied to the quantitative analysis of the epidemic trends and the suppression effect of emotional contagion in different countries. Our model can be modified for further research to study other social factors and intervention policies in the COVID-19 pandemic or future epidemics.

28 March 2022 in Entropy
Verified
Journal Article
Open access
PDF file
DSDaming Shi
Daming Shi
JTJunbo Tong
Junbo Tong
YLYi Liu
Yi Liu
WFWenhui Fan
Wenhui Fan
With the development and appliance of multi-agent systems, multi-agent cooperation is becoming an important problem in artificial intelligence. Multi-agent reinforcement learning (MARL) is one of the most effective methods for solving multi-agent cooperative tasks. However, the huge sample complexity of traditional reinforcement learning methods results in two kinds of training waste in MARL for cooperative tasks: all homogeneous agents are trained independently and repetitively, and multi-agent systems need training from scratch when adding a new teammate. To tackle these two problems, we propose the knowledge reuse methods of MARL. On the one hand, this paper proposes sharing experience and policy within agents to mitigate training waste. On the other hand, this paper proposes reusing the policies learned by original teams to avoid knowledge waste when adding a new agent. Experimentally, the Pursuit task demonstrates how sharing experience and policy can accelerate the training speed and enhance the performance simultaneously. Additionally, transferring the learned policies from the N-agent enables the (N+1)–agent team to immediately perform cooperative tasks successfully, and only a minor training resource can allow the multi-agents to reach optimal performance identical to that from scratch.

4 July 2025 in International Journal of Robust and Nonlinear Control
Verified
Journal Article
Closed access
JTJunbo Tong
Junbo Tong
SDShuhan Du
Shuhan Du
WFWenhui Fan
Wenhui Fan

28 May 2023 in ACM Transactions on Autonomous and Adaptive Systems
Verified
Journal Article
Open access
JTJunbo Tong
Junbo Tong
DSDaming Shi
Daming Shi
YLYi Liu
Yi Liu
WFWenhui Fan
Wenhui Fan
In the implementation of deep reinforcement learning (DRL), action persistence strategies are often adopted so agents maintain their actions for a fixed or variable number of steps. The choice of the persistent duration for agent actions usually has notable effects on the performance of reinforcement learning algorithms. Aiming at the research gap of global dynamic optimal action persistence and its application in multi-agent systems, we propose a novel framework: global dynamic action persistence (GLDAP), which achieves global action persistence adaptation for deep reinforcement learning. We introduce a closed-loop method that is used to learn the estimated value and the corresponding policy of each candidate action persistence. Our experiment shows that GLDAP achieves an average of 2.5%~90.7% performance improvement and 3~20 times higher sampling efficiency over several baselines across various single-agent and multi-agent domains. We also validate the ability of GLDAP to determine the optimal action persistence through multiple experiments.

19 September 2023 in Transactions of the Institute of Measurement and Control
Verified
Journal Article
Closed access
JTJunbo Tong
Junbo Tong
SDShuhan Du
Shuhan Du
WFWenhui Fan
Wenhui Fan
YCYueting Chai
Yueting Chai
Robust model predictive control (RMPC) is an effective technology for controlling uncertain systems while robustly handling constraints, and its closed-loop performance heavily relies on the selection of objective functions. However, the objective functions are typically chosen to be close to the real control objectives, despite an objective function that leads to less conservative constraints often provides better closed-loop performance. In this paper, we propose an automatic tuning framework for RMPC in iterative tasks. In particular, we parameterize RMPC and develop a Bayesian optimization (BO) method to tune it by solving a black-box optimization problem. We then introduce an efficient transfer learning framework within BO, which speeds up the searching process and enhances the controller performance. The effectiveness of the proposed tuning framework is illustrated on numerical examples.

13 September 2025 in Applied Soft Computing
Verified
Journal Article
Closed access
JTJunbo Tong
Junbo Tong
SDShuhan Du
Shuhan Du
DSDaming Shi
Daming Shi
WFWenhui Fan
Wenhui Fan