Non-linear Continuous Action Spaces for Reinforcement Learning in Type 1 Diabetes.
Chirath HettiarachchiNicolò MalaguttiChristopher J. NolanHanna SuominenElena DaskalakiPublished in: AI (2022)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- real valued
- continuous state
- continuous state spaces
- action selection
- reinforcement learning methods
- control policies
- stochastic processes
- state action
- function approximators
- machine learning
- continuous action
- single agent
- markov decision process
- function approximation
- multi agent
- skill learning
- optimal control
- heuristic search
- model free
- temporal difference
- optimal policy
- dynamic environments
- markov chain
- dynamic programming
- decision making
- learning algorithm