Ye-Feng Liu

Counterfactual Multi-Agent Credit Assignment Optimization Fused with Spatial Causal Adjacency Matrix

Counterfactual Multi-Agent Policy Gradients (COMA) are often hampered by dense, irrelevant noise in the centralized critic, which stems from the full-conditioning assumption in high-dimensional action spaces and results in unstable gradient estimation. To address this fundamental limitation, this paper introduces SCAM-...