PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning - Lifelong.
Mehul DamaniZhiyao LuoEmerson WenzelGuillaume SartorettiPublished in: CoRR (2020)
Keyphrases
- path finding
- multi agent learning
- reinforcement learning
- agents and multi agent systems
- heuristic search
- complex domains
- path planning
- multi agent
- game theory
- search algorithm
- state space
- rl algorithms
- learning agents
- linear programming
- support vector
- hill climbing
- function approximation
- rule learning
- artificial intelligence
- markov decision processes
- learning algorithm
- optimal path
- reinforcement learning algorithms
- objective function
- background knowledge
- optimal policy
- dynamic environments
- simulated annealing
- fuzzy logic
- optimal solution