SACHI enriches agent representations via graph transformer convolutions over inter-agent graphs to enable holistic information integration, outperforming baselines across five cooperative tasks with statistical significance.
Graph convolutional value decomposi- tion in multi-agent reinforcement learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2roles
background 1polarities
background 1representative citing papers
LTS-CG infers latent temporal sparse coordination graphs from historical observations to enable efficient, uncertainty-aware agent coordination in MARL with complexity linear in the number of agents.
citing papers explorer
-
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
SACHI enriches agent representations via graph transformer convolutions over inter-agent graphs to enable holistic information integration, outperforming baselines across five cooperative tasks with statistical significance.
-
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
LTS-CG infers latent temporal sparse coordination graphs from historical observations to enable efficient, uncertainty-aware agent coordination in MARL with complexity linear in the number of agents.