Reinforcement Learning-Based Approximate Optimal Control for Attitude Reorientation Under State Constraints.
Hongyang DongXiaowei ZhaoHaoyang YangPublished in: IEEE Trans. Control. Syst. Technol. (2021)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- dynamic programming
- state space
- risk sensitive
- feedback control
- control strategy
- infinite horizon
- brownian motion
- class of nonlinear systems
- function approximation
- optimal control problems
- actor critic
- neural network
- partially observable
- constraint programming
- lyapunov function
- linear quadratic
- constrained optimization
- temporal difference
- markov decision processes
- state action
- linear programming
- learning algorithm