Sep 2026
Efficient Communication With Skill Neurons in Decentralized Multi-Agent Reinforcement Learning.
CSN is proposed, which enables efficient Communication with Skill Neurons in decentralized MARL by exchanging the essential components of learned knowledge at neuron level by communicating only a sparse subset of model parameters and doing so intermittently.
Jiahua Lan, Li Shen, Ruijun Liu et al.
· IEEE Transactions on Pattern... · 0 citations