Closed-loop control of a noisy qubit with reinforcement learning.
Yongcheng DingXi ChenJosé Rafael Magdalena BeneditoJosé D. Martín-GuerreroPublished in: Mach. Learn. Sci. Technol. (2023)
Keyphrases
- reinforcement learning
- function approximation
- control problems
- temporal difference learning
- learning algorithm
- temporal difference
- learning process
- neural network
- noisy environments
- state space
- dynamic programming
- multi agent reinforcement learning
- markov decision processes
- function approximators
- robotic control
- reinforcement learning algorithms
- action space
- robot control
- policy search
- real time
- direct policy search
- noise free
- model free
- incomplete data
- multi agent
- multiscale
- artificial intelligence
- information retrieval