A model-free deep integral policy iteration structure for robust control of uncertain systems.
Ding WangAo LiuJunfei QiaoPublished in: Int. J. Syst. Sci. (2024)
Keyphrases
- model free
- policy iteration
- reinforcement learning
- markov decision processes
- function approximation
- impedance control
- sample path
- optimal control
- reinforcement learning algorithms
- policy evaluation
- least squares
- temporal difference
- optimal policy
- average reward
- fixed point
- support vector machine
- markov decision problems
- temporal difference learning
- e learning
- feature selection
- decision making
- markov decision process
- state space
- finite state
- machine learning
- control strategy