TIDE: Time-relevant deep reinforcement learning for routing optimization.
Penghao SunYuxiang HuJulong LanLe TianMin ChenPublished in: Future Gener. Comput. Syst. (2019)
Keyphrases
- reinforcement learning
- logistics distribution
- function approximation
- optimization problems
- optimization model
- neural network
- optimization process
- routing algorithm
- optimization algorithm
- state space
- learning algorithm
- global optimization
- artificial neural networks
- genetic algorithm
- network topology
- data sets
- robotic control
- temporal difference
- action selection
- machine learning
- routing problem
- optimal control
- evaluation function
- ad hoc networks
- optimization method
- routing protocol
- learning process
- evolutionary algorithm