Multi-Agent Path Finding: Policies Instead of Plans.
Jakub MestekRoman BartákPublished in: ICAART (1) (2024)
Keyphrases
- path finding
- multi agent
- single agent
- heuristic search
- path planning
- search algorithm
- virtual endoscopy
- multi agent systems
- hill climbing
- optimal policy
- reinforcement learning agents
- planning problems
- reinforcement learning
- robocup rescue
- multiple agents
- rule learning
- state space
- dynamic programming
- search space
- partially observable markov decision processes
- error rate
- knowledge discovery
- computational complexity
- neural network