activity
20222026
most citedLearning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples

43 citations · 53 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning

Wei Duan, Junyu Xuan, En Yu +2

Coordination graphs are a central abstraction in cooperative multi-agent reinforcement learning (MARL), yet existing sparse-graph learners lack a theoretically grounded mechanism t…