ARMS is an automatic reward-shaping framework for sparse-reward MARL that uses trajectory ranking and conditional best-response reasoning to preserve Nash equilibria while improving sampling efficiency in pathfinding tasks.
Ng and Daishi Harada and Stuart Russell , editor =
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
-
ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
ARMS is an automatic reward-shaping framework for sparse-reward MARL that uses trajectory ranking and conditional best-response reasoning to preserve Nash equilibria while improving sampling efficiency in pathfinding tasks.