PC3D trains decentralized policies to recover and use personalized coordination context from local histories, enabling higher returns than baselines on variable-roster cooperative MARL tasks with both seen and unseen team sizes.
HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation
PC3D trains decentralized policies to recover and use personalized coordination context from local histories, enabling higher returns than baselines on variable-roster cooperative MARL tasks with both seen and unseen team sizes.