MLP technique based reinforcement learning control of discrete pure-feedback systems.
Yu ZhangShixing WangPublished in: Neurocomputing (2015)
Keyphrases
- reinforcement learning
- control strategies
- human operators
- control problems
- autonomous systems
- control system
- management system
- markov decision processes
- control strategy
- computer systems
- learning algorithm
- neural network
- optimal policy
- optimal control
- action selection
- temporal difference
- relevance feedback
- expert systems
- robot control