3 papers
cs.LG2025
Explainable Graph Neural Networks via Structural Externalities
Lijun Wu, Dong Hao, Zhiyi Fan
Graph Neural Networks (GNNs) have achieved outstanding performance across a wide range of graph-related tasks. However, their "black-box" nature poses significant challenges to the…
cs.MA2024
Backpropagation Through Agents
Zhiyuan Li, Wenshuai Zhao, Lijun Wu +1
A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of a…
cs.MA2024
AgentMixer: Multi-Agent Correlated Policy Factorization
Zhiyuan Li, Wenshuai Zhao, Lijun Wu +1
In multi-agent reinforcement learning, centralized training with decentralized execution (CTDE) methods typically assume that agents make decisions based on their local observation…