Reinforcement Learning for Continuous Control: A Quantum Normalized Advantage Function Approach.
Yaofu LiuChang XuSiyuan JinPublished in: QSW (2023)
Keyphrases
- reinforcement learning
- control policy
- control problems
- optimal control
- robot control
- piecewise linear
- control strategies
- adaptive control
- control method
- piecewise constant
- state space
- function approximation
- control strategy
- robotic control
- control policies
- action space
- continuous state and action spaces
- transition model
- dynamic programming
- function approximators
- continuous functions
- control theory
- data acquisition
- learning algorithm
- model free