Double Deep-Q Learning-Based Output Tracking of Probabilistic Boolean Control Networks.
Antonio AcerneseAmol YerudkarLuigi GlielmoCarmen Del VecchioPublished in: IEEE Access (2020)
Keyphrases
- learning algorithm
- bayesian networks
- causal networks
- cooperative
- real time
- object tracking
- reinforcement learning
- kalman filter
- input data
- network structure
- generative model
- multi agent
- particle filter
- control system
- visual tracking
- feedback control
- uncertain data
- probabilistic networks
- function approximation
- optimal control
- control method
- boolean networks
- boolean expressions
- stochastic approximation
- action selection
- control strategies
- boolean functions
- control strategy
- appearance model
- dynamic programming
- state space
- human body