Actor-Critic Reinforcement Learning for Linear Longitudinal Output Control of a Road Vehicle.
Luca PuccettiChristian RathgeberSören HohmannPublished in: ITSC (2019)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- control problems
- lyapunov stability
- temporal difference
- policy gradient
- function approximation
- road vehicles
- neuro fuzzy
- reinforcement learning algorithms
- control system
- policy iteration
- control strategy
- approximate dynamic programming
- adaptive control
- dynamic programming
- control policy
- function approximators
- gradient method
- model free
- evaluation function
- action selection
- temporal difference learning
- state space
- control strategies
- real time
- supervised learning
- computer vision
- control method
- partially observable markov decision processes
- closed loop
- markov decision processes
- average reward
- multi agent
- learning algorithm
- machine learning