Time Optimal Control of Mini-submarine Missile Based on Deep Reinforcement Learning.
Canhui TaoZhiping SongBaoshou WangPublished in: AsiaSim (2) (2022)
Keyphrases
- optimal control
- reinforcement learning
- control problems
- feedback control
- dynamic programming
- risk sensitive
- optimal control problems
- control system
- control law
- lyapunov function
- class of nonlinear systems
- function approximation
- approximate dynamic programming
- infinite horizon
- model free
- reinforcement learning algorithms
- control strategy
- actor critic
- machine learning
- brownian motion
- rl algorithms
- target tracking
- policy iteration
- reinforcement learning methods
- queueing systems
- policy gradient
- learning problems
- state space
- linear quadratic
- learning algorithm
- neural network
- continuous stirred tank reactor