Pengcheng Dai

Southeast University

Papers

2

Total Citations

49

H-Index

2

About

Pengcheng Dai is a leading researcher in multi-agent reinforcement learning (MARL), with a focus on developing scalable and theoretically grounded algorithms for cooperative and networked systems. His major contributions include the introduction of the DTDE (Distributed Training, Decentralized Execution) framework, a novel cooperative MARL paradigm that addresses key challenges in agent coordination and policy learning. This work, published in 2021, has already garnered 44 citations, reflecting its significant impact on the field. More recently, Dai has advanced the state of the art with a distributed neural policy gradient algorithm that ensures global convergence in networked multi-agent settings—a critical step beyond linear function approximation methods. His research bridges the gap between practical multi-agent systems and rigorous theoretical guarantees, offering new pathways for applications in robotics, autonomous driving, and distributed control. By tackling both the expressiveness and convergence challenges in MARL, Pengcheng Dai is shaping the future of intelligent, cooperative decision-making in complex environments.

Research Focus

Key Achievements

2
H-Index
2
Papers
49
Total Citations
25
Avg Citations/Paper
🏆 Most Cited Paper
DTDE: A new cooperative multi-agent reinforcement learning framework
44 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Southeast University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago