Critic-over-Actor-Critic Modeling: Finding Optimal Strategy in ICU Environments.
Riazat RyanMing ShaoPublished in: Big Data (2022)
Keyphrases
- actor critic
- optimal strategy
- reinforcement learning
- policy gradient
- approximate dynamic programming
- temporal difference
- optimal control
- neuro fuzzy
- reinforcement learning algorithms
- gradient method
- monte carlo
- function approximation
- policy iteration
- decision problems
- step size
- markov decision processes
- average reward
- natural actor critic
- model free
- infinite horizon
- mathematical models
- evaluation function
- experimental data
- particle filter