SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding.
Yutong WangBairan XiangShinan HuangGuillaume SartorettiPublished in: AAMAS (2023)
Keyphrases
- path finding
- imitation learning
- reinforcement learning
- multi agent
- single agent
- path planning
- heuristic search
- search algorithm
- state space
- reinforcement learning methods
- rule learning
- hill climbing
- maximum margin
- humanoid robot
- robotic systems
- learning algorithm
- optimal path
- dynamic programming
- real valued
- learning problems
- social network analysis
- web scale
- search space
- neural network