The paper proves that communication in decentralized critics adds variance to policy gradients and introduces baseline plus KL techniques that reduce this variance and improve learning.
Multi-agent deep reinforcement learning: a survey
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning
The paper proves that communication in decentralized critics adds variance to policy gradients and introduces baseline plus KL techniques that reduce this variance and improve learning.