MARL produces transferable rendezvous strategies in vortical flows that outperform naive navigation by exploiting fluid kinematics to prevent agents from becoming trapped in separate vortices.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-agent rendezvous in fluid flows via reinforcement learning
MARL produces transferable rendezvous strategies in vortical flows that outperform naive navigation by exploiting fluid kinematics to prevent agents from becoming trapped in separate vortices.