Online reinforcement learning for condition-based group maintenance using factored Markov decision processes.
Jianyu XuBin LiuXiujie ZhaoXiao-Lin WangPublished in: Eur. J. Oper. Res. (2024)
Keyphrases
- factored markov decision processes
- reinforcement learning
- state space
- function approximation
- markov decision problems
- sufficient conditions
- markov decision processes
- learning algorithm
- linear programming
- lower bound
- supervised learning
- optimal policy
- state variables
- model free
- action space
- dynamic programming
- steady state
- reinforcement learning algorithms