Hybrid Control Policy for Artificial Pancreas via Ensemble Deep Reinforcement Learning.
Wenzhou LvTianyu WuLuolin XiongLiang WuJian ZhouYang TangFeng QianPublished in: CoRR (2023)
Keyphrases
- control policy
- reinforcement learning
- approximate dynamic programming
- admission control
- long run
- control policies
- learning algorithm
- artificial intelligent systems
- batch mode
- state space
- function approximation
- ensemble learning
- optimal policy
- random forests
- temporal difference
- neural network
- real valued
- multi agent
- training data
- machine learning
- model free
- action selection
- random forest
- ensemble classifier
- classifier ensemble
- markov chain
- traffic signal
- feature selection