Adaptively fusing two value-decomposition policies with a KL constraint improves cooperative MARL performance on matrix game, SMAC, and predator-prey tasks.
In Add-HPF-WQ, WQMIX[Rashid et al., 2020] is chosen as πα in Eq.(4) of the main text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Heterogeneous Value Decomposition Policy Fusion for Multi-Agent Cooperation
Adaptively fusing two value-decomposition policies with a KL constraint improves cooperative MARL performance on matrix game, SMAC, and predator-prey tasks.