Double Q-Learning for Citizen Relocation During Natural Hazards.
Alysson Ribeiro Da SilvaPublished in: CoRR (2022)
Keyphrases
- multi agent
- e government
- learning rate
- cooperative
- state space
- learning algorithm
- public services
- digital government
- reinforcement learning
- real world
- function approximation
- government agencies
- model free
- reinforcement learning algorithms
- potential field
- decision making
- early warning
- vehicle routing
- temporal difference learning