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.
Approximation capabilities of multilayer feedforward networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.