Li Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Li Zeng has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Binfan Xing
School of Information Science and Technology, Zhengzhou Normal University, Zhengzhou, China
1 shared publication - Gang Yu
School of Information Science and Technology, Zhengzhou Normal University, Zhengzhou, China
1 shared publication - Jiaxing Hu
School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, Wollongong, NSW, Australia
1 shared publication - Qiang Zhu
School of Computer and Artificial Intelligence, ZhengZhou University, Zhengzhou, China
1 shared publication - Yuchu He
School of Information Science and Technology, Zhengzhou Normal University, Zhengzhou, China
1 shared publication
Latest Publications
- Open Access
- 29 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 196-200
Deep Reinforcement Learning for Traffic Signal Control Using Fairness-Aware PPO with an Excess-Wait Penalty
Deep reinforcement learning for traffic signal control often optimizes aggregate efficiency while leaving a subset of vehicles with excessive waiting. This paper proposes a fairness-aware PPO controller that adds lane-level long-wait vehicle counts to the state and introduces an excess-wait penalty into the reward. A coefficient γ controls the efficiency–fairness trade-off. In SUMO experiments on an isolated intersection, PPO-Ours (γ = 0.20) reduces maximum waiting time from 688.33 s to 480.23 s and waiting-time standard deviation from 158.87 s to 98.45 s relative to PPO-Basic, while preserving competitive average-queue performance. Ablation results show that γ provides a practical trade-off knob rather than a universally optimal setting under all metrics.
- 29 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 196-200
Open AccessDeep Reinforcement Learning for Traffic Signal Control Using Fairness-Aware PPO with an Excess-Wait Penalty
Deep reinforcement learning for traffic signal control often optimizes aggregate efficiency while leaving a subset of vehicles with excessive waiting. This paper proposes a fairness-aware PPO controller that adds lane-level long-wait vehicle counts to the state and introduces an excess-wait penalty into the reward. A coefficient γ controls the efficiency–fairness trade-off. In SUMO experiments on an isolated intersection, PPO-Ours (γ = 0.20) reduces maximum waiting time from 688.33 s to 480.23 s and waiting-time standard deviation from 158.87 s to 98.45 s relative to PPO-Basic, while preserving competitive average-queue performance. Ablation results show that γ provides a practical trade-off knob rather than a universally optimal setting under all metrics.