Combinatorial Q-Learning for Condition-Based Infrastructure Maintenance.
Akira TanimotoPublished in: IEEE Access (2021)
Keyphrases
- reinforcement learning
- function approximation
- software maintenance
- cooperative
- sufficient conditions
- learning algorithm
- multi agent
- state space
- optimal policy
- reinforcement learning algorithms
- learning rate
- multi agent reinforcement learning
- model free
- dynamic programming
- temporal difference learning
- preventive maintenance
- computing environments
- knowledge acquisition
- information exchange
- case study
- genetic algorithm
- action selection
- data sets
- stochastic approximation
- real time