Defines stable points to diagnose suboptimal convergence in value factorization MARL and introduces MRVF to iteratively eliminate inferior actions by rendering them unstable.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning
Defines stable points to diagnose suboptimal convergence in value factorization MARL and introduces MRVF to iteratively eliminate inferior actions by rendering them unstable.