A MARL framework that uses an active-contour-inspired reward to train UAV swarms for collision avoidance without credit assignment or observation sharing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Learning Framework For Cooperative Collision Avoidance of UAV Swarms Leveraging Domain Knowledge
A MARL framework that uses an active-contour-inspired reward to train UAV swarms for collision avoidance without credit assignment or observation sharing.