Learning Parameterized Prescription Policies and Disease Progression Dynamics using Markov Decision Processes.
Henghui ZhuTingting XuIoannis Ch. PaschalidisPublished in: ACC (2019)
Keyphrases
- markov decision processes
- optimal policy
- reinforcement learning
- macro actions
- model based reinforcement learning
- partially observable
- state space
- decision processes
- dynamic programming
- markov decision process
- markov decision problems
- average cost
- learning algorithm
- reward function
- transition matrices
- real time dynamic programming
- policy iteration
- total reward