Persistent coverage of UAVs based on deep reinforcement learning with wonderful life utility.
Zhaomei SunNan WangHong LinXiaojun ZhouPublished in: Neurocomputing (2023)
Keyphrases
- reinforcement learning
- utility function
- sequential decision problems
- state space
- function approximation
- unmanned aerial vehicles
- temporal difference
- learning algorithm
- model free
- optimal policy
- everyday life
- reinforcement learning algorithms
- transfer learning
- daily life
- aerial vehicles
- mission planning
- path planning
- control algorithm
- action selection
- action space
- fitted q iteration
- autonomous learning
- multi agent reinforcement learning
- databases
- partially observable
- learning capabilities
- decision makers
- supervised learning
- dynamic programming
- multi agent
- case study
- machine learning