SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding.
Yutong WangBairan XiangShinan HuangGuillaume SartorettiPublished in: CoRR (2023)
Keyphrases
- path finding
- imitation learning
- reinforcement learning
- multi agent
- single agent
- path planning
- search algorithm
- heuristic search
- hill climbing
- state space
- markov decision processes
- humanoid robot
- dynamic programming
- maximum margin
- tabu search
- evaluation function
- optimal path
- reinforcement learning algorithms
- rule learning
- reinforcement learning methods