Policy Gradient-based Integral Reinforcement Learning for Optimal Control Design of Nonaffine Morphing Aircraft Systems.
Hanna LeeSeonghun KimYoudan KimPublished in: MED (2020)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- infinite horizon
- feedback control
- actor critic
- risk sensitive
- dynamic programming
- control strategy
- policy gradient
- policy iteration
- stochastic control
- optimal policy
- state space
- class of nonlinear systems
- neural network
- average cost
- action selection
- brownian motion
- markov decision process
- model free
- control law
- machine learning