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.
Reducing overestimation bias in multi-agent domains using double centralized critics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.
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.
-
ERPPO: Entropy Regularization-based Proximal Policy Optimization
ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.