GTDE dynamically groups agents during training using Gumbel-Sigmoid sampling, enabling decentralized execution that outperforms CTDE and DTDE on large-scale multi-agent benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic
GTDE dynamically groups agents during training using Gumbel-Sigmoid sampling, enabling decentralized execution that outperforms CTDE and DTDE on large-scale multi-agent benchmarks.