PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning.
Guillaume SartorettiJustin KerrYunfei ShiGlenn WagnerT. K. Satish KumarSven KoenigHowie ChosetPublished in: IEEE Robotics Autom. Lett. (2019)
Keyphrases
- path finding
- multi agent learning
- reinforcement learning
- agents and multi agent systems
- complex domains
- multi agent
- path planning
- game theory
- heuristic search
- search algorithm
- rl algorithms
- learning agents
- linear programming
- state space
- optimal path
- support vector
- artificial intelligence
- hill climbing
- function approximation
- learning algorithm
- reinforcement learning algorithms
- rule learning
- objective function
- simulated annealing
- model free
- supervised learning
- semi supervised
- dynamic programming
- optimal policy
- complexity analysis
- search space
- optimal solution
- data mining