Yuduo Zheng — accepted AI-conference papers

2026

EVA-Gen: When Perception Learns from Value via Generative Models in Decentralized Multi-Agent Systems

Yuduo Zheng, XueFeng Du, Yanqi Cheng, Li Yin, Fengqi Li

IJCAI 2026

Decentralized Multi Agent Reinforcement Learning (MARL) faces a fundamental dilemma in real world deployments: agents must operate under epistemic fragmentation, where local observations are severely occluded, while navigating heterogeneous value landscapes, where sparse, critical events carry dispr

Cited by 0 Scholar ↗

2026

IEC: When Information-Driven Exploration Meets Spectral Consensus via Primal–Dual Reward Regularization in Decentralized Multi-Agent RL

Jiajun Wu, Xuefeng Du, Yuduo Zheng, Fengqi Li

ICML 2026poster

Decentralized multi-agent reinforcement learning faces a persistent exploration–coordination tension: intrinsic rewards promote exploration under sparse feedback, yet effective cooperation requires agents’ behaviors to remain consistent over a limited communication graph. Existing methods often comb…

Cited by 0 Source ↗Scholar ↗