SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding.
Yutong WangBairan XiangShinan HuangGuillaume SartorettiPublished in: IROS (2023)
Keyphrases
- imitation learning
- path finding
- reinforcement learning
- multi agent
- single agent
- path planning
- heuristic search
- search algorithm
- reinforcement learning methods
- robotic systems
- learning algorithm
- maximum margin
- state space
- hill climbing
- markov decision processes
- machine learning
- humanoid robot
- reinforcement learning algorithms
- multi modal
- concept learning
- learning classifier systems
- transfer learning