Abstract
With the advancements in reinforcement learning (RL), new variants of this artificial intelligence approach have been introduced in the literature. This has led to increased interest in using RL to address complex issues in diabetes management. Using RL, a decision maker (or agent) observes decision-making factors (or state) from the dynamic operating environment, selects actions, and subsequently receives delayed rewards. The agent adapts its actions to changes in the operating environment to maximize its cumulative reward and improve system performance. This paper presents how various variants of RL have been used to improve diabetes management, such as a higher time in range during which the blood glucose level is within the normal range and a higher similarity between RL and physician's policies. Key highlights focus on the application of RL in diabetes management, including a taxonomy of the attributes of RL (e.g., roles and advantages), essential elements for training (e.g., data and simulators), representations of diabetes attributes in RL models, and variants of RL algorithms. In addition, this paper discusses open issues and potential future developments in the use of RL in diabetes management.
Original language | English |
---|---|
Pages (from-to) | 28391-28415 |
Number of pages | 25 |
Journal | IEEE Access |
Volume | 11 |
Early online date | 20 Mar 2023 |
DOIs | |
Publication status | Published - 24 Mar 2023 |
Keywords
- Actor-critic reinforcement learning
- applied reinforcement learning
- deep Q-network
- deep reinforcement learning
- diabetes
- Markov decision process
- multi-agent reinforcement learning
- reinforcement learning
- Q-learning
- Reinforcement learning
- Glucose
- Insulin
- Blood
- Deep learning
- Data models
- Diabetes
- Multi-agent systems
- General Computer Science
- General Materials Science
- General Engineering
- Electrical and Electronic Engineering