Lin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lin Li has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wei
Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China
9 shared publications - Jiye Liang
Shanxi University
7 shared publications - Yujia Zhang
School of Computer Science and Technology, North University of China, Taiyuan, 030051, Shanxi, China
4 shared publications - Da Wang
Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China
2 shared publications - Lijun Zhang
Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan, 030006, Shanxi, China
2 shared publications - Binchao Ma
Shanxi University, Taiyuan, China
1 shared publication
Latest Publications
- 15 October 2026
- Published by Elsevier in Neural Networks
- Vol. 206 (Pt A) , 109769
Structured goal-guided reinforcement learning with large language models
- 15 October 2026
- Published by Elsevier in Neural Networks
- Vol. 206 (Pt A) , 109769
Structured goal-guided reinforcement learning with large language models
- Open Access
- 21 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 48-57
AGOD: Enhancing Multi-Agent Generalization via Attribution-Guided Observation Dropout
- 21 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 48-57
Open AccessAGOD: Enhancing Multi-Agent Generalization via Attribution-Guided Observation Dropout
- 22 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 108018
Pseudo-distribution elite critics: Enhancing accuracy in reinforcement learning value estimation
- 22 August 2025
- Published by Elsevier in Neural Networks
- Vol. 193, 108018
Pseudo-distribution elite critics: Enhancing accuracy in reinforcement learning value estimation
- 11 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107342
Rethinking exploration–exploitation trade-off in reinforcement learning via cognitive consistency
- 11 March 2025
- Published by Elsevier in Neural Networks
- Vol. 187, 107342
Rethinking exploration–exploitation trade-off in reinforcement learning via cognitive consistency
- 25 June 2024
- Published by Elsevier in Neural Networks
- Vol. 178, 106483
A unified framework to control estimation error in reinforcement learning
- 25 June 2024
- Published by Elsevier in Neural Networks
- Vol. 178, 106483
A unified framework to control estimation error in reinforcement learning
- 13 May 2024
- Published by Elsevier in Information Sciences
- Vol. 675
Controlling estimation error in reinforcement learning via Reinforced Operation
- 13 May 2024
- Published by Elsevier in Information Sciences
- Vol. 675
Controlling estimation error in reinforcement learning via Reinforced Operation
- 22 February 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (5) , 2327-2349
Re-attentive experience replay in off-policy reinforcement learning
- 22 February 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (5) , 2327-2349
Re-attentive experience replay in off-policy reinforcement learning
- 10 August 2023
- Published by Elsevier in Information Sciences
- Vol. 647, 119494
Multi-actor mechanism for actor-critic reinforcement learning
- 10 August 2023
- Published by Elsevier in Information Sciences
- Vol. 647, 119494
Multi-actor mechanism for actor-critic reinforcement learning
- 24 September 2022
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 13 (12) , 4033-4042
Hierarchical metric learning with intra-level and inter-level regularization
- 24 September 2022
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 13 (12) , 4033-4042
Hierarchical metric learning with intra-level and inter-level regularization
- Open Access
- 9 February 2020
- Published by MDPI AG in Electronics
- Vol. 9 (2) , 298
Driver’s Social Relationship Based Clustering and Transmission in Vehicle Ad Hoc Networks (VANETs)
Clustering is a technique for dividing a network into different group of nodes and managing the transmission of data among the interacting nodes, to improve the effectiveness and safety of information transfer. Clustering have been well studied and applied in traditional mobile networks. However, vehicle networks have short connection time, frequently changing topology, and other unique properties that conventional clustering cannot transfer well. The vehicle nodes in Vehicle Ad-hoc Networks (VANETs) are most directly affected by the surrounding vehicle nodes and exchanged information with them. However, this will cause network congestion or even the spread of malicious messages. The inclusion of vehicle’s (driver’s) social relationships in vehicle communication clustering will increase the degree of trust between vehicle nodes, making communication more purposeful and accurate. This study proposed a new clustering for vehicle networks that is based on drivers’ social relationship combined with the instantaneous position and speed of the vehicle node. Simulation results showed that this clustering method can improve the effectiveness of information transmission and increase the utilization of the application layer.
- 9 February 2020
- Published by MDPI AG in Electronics
- Vol. 9 (2) , 298
Open AccessDriver’s Social Relationship Based Clustering and Transmission in Vehicle Ad Hoc Networks (VANETs)
Clustering is a technique for dividing a network into different group of nodes and managing the transmission of data among the interacting nodes, to improve the effectiveness and safety of information transfer. Clustering have been well studied and applied in traditional mobile networks. However, vehicle networks have short connection time, frequently changing topology, and other unique properties that conventional clustering cannot transfer well. The vehicle nodes in Vehicle Ad-hoc Networks (VANETs) are most directly affected by the surrounding vehicle nodes and exchanged information with them. However, this will cause network congestion or even the spread of malicious messages. The inclusion of vehicle’s (driver’s) social relationships in vehicle communication clustering will increase the degree of trust between vehicle nodes, making communication more purposeful and accurate. This study proposed a new clustering for vehicle networks that is based on drivers’ social relationship combined with the instantaneous position and speed of the vehicle node. Simulation results showed that this clustering method can improve the effectiveness of information transmission and increase the utilization of the application layer.