PRIMAL$_2$: Pathfinding Via Reinforcement and Imitation Multi-Agent Learning - Lifelong.
Mehul DamaniZhiyao LuoEmerson WenzelGuillaume SartorettiPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- multi agent learning
- path finding
- reinforcement learning
- agents and multi agent systems
- multi agent
- complex domains
- heuristic search
- game theory
- search algorithm
- path planning
- state space
- linear programming
- function approximation
- learning agents
- rl algorithms
- rule learning
- support vector
- hill climbing
- cooperative
- artificial intelligence
- objective function
- reinforcement learning algorithms
- learning algorithm
- model free
- real valued
- optimal solution
- supervised learning
- domain knowledge
- search space
- computational complexity