Zero-sum game-based neuro-optimal control of modular robot manipulators with uncertain disturbance using critic only policy iteration.
Bo DongTianjiao AnXinye ZhuYuanchun LiKeping LiuPublished in: Neurocomputing (2021)
Keyphrases
- optimal control
- robot manipulators
- policy iteration
- actor critic
- stochastic games
- control scheme
- control strategy
- average reward
- infinite horizon
- control problems
- dynamic programming
- reinforcement learning
- policy gradient
- dynamic model
- sliding mode control
- markov decision processes
- approximate dynamic programming
- decision making
- temporal difference
- artificial neural networks
- average cost
- sliding mode
- markov decision problems
- neuro fuzzy
- reinforcement learning algorithms
- model free
- neural network
- control system
- fuzzy neural network
- control law
- markov decision process
- pid controller
- control algorithm
- radial basis function
- mathematical model
- data mining