Maintenance strategy optimization using a continuous-state partially observable semi-Markov decision process.
Yifan ZhouLin MaJoseph MathewYong SunRodney WolffPublished in: Microelectron. Reliab. (2011)
Keyphrases
- partially observable
- continuous state
- reinforcement learning
- markov decision processes
- partially observable markov decision processes
- finite state
- action space
- dec pomdps
- state space
- hidden state
- belief state
- markov decision problems
- decision problems
- dynamical systems
- control policies
- infinite horizon
- robot navigation
- optimal policy
- reward function
- function approximation
- reinforcement learning algorithms
- policy iteration
- control policy
- domain specific