Policy Optimization by Neural Network and Its Application to Queueing Allocation Problem.
Hisashi SatoYutaka MatsumotoNorio OkinoPublished in: ICANNGA (1995)
Keyphrases
- neural network
- state dependent
- optimization algorithm
- optimization process
- global optimization
- pattern recognition
- image reconstruction from projections
- optimization problems
- optimal policy
- priority scheduling
- feed forward
- bp neural network
- neural nets
- highly non linear
- steady state
- back propagation
- training algorithm
- neural network is trained
- learning vector quantization
- arrival rate
- infinite horizon
- activation function
- network model
- optimization methods
- fault diagnosis
- optimization method