A hierarchical graph transformer with layer-by-layer feedback reinforcement learning beats rule-based, MILP, and GNN baselines in a two-stage dynamic Colonel Blotto resource allocation game on graphs.
Finite-time dynamic alloca- tion and control in multiagent coordination for target tracking,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
HGFormer: A Hierarchical Graph Transformer Framework for Two-Stage Colonel Blotto Games via Reinforcement Learning
A hierarchical graph transformer with layer-by-layer feedback reinforcement learning beats rule-based, MILP, and GNN baselines in a two-stage dynamic Colonel Blotto resource allocation game on graphs.