A joint reinforcement learning framework that co-trains robot movement policy and global edge-cost guidance to beat strong baselines in lifelong multi-agent path finding with rotation and safety constraints.
AAMAS , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations
A joint reinforcement learning framework that co-trains robot movement policy and global edge-cost guidance to beat strong baselines in lifelong multi-agent path finding with rotation and safety constraints.