ACPO decomposes the joint policy gradient into per-agent terms allowing independent actor training that collectively forms a joint gradient step in CTDE-based MARL.
Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach , booktitle =
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
-
ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning
ACPO decomposes the joint policy gradient into per-agent terms allowing independent actor training that collectively forms a joint gradient step in CTDE-based MARL.