Reinforcement learning-basierte Patchpriorisierung zur beschleunigten Segmentierung von hochauflösenden Endoskopievideodaten.
Samuel SchüttlerFrederic MadestaThomas RöschRené WernerRüdiger SchmitzPublished in: Bildverarbeitung für die Medizin (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- multi agent
- markov decision processes
- robotic control
- temporal difference learning
- temporal difference
- optimal policy
- neural network
- reinforcement learning algorithms
- learning algorithm
- machine learning
- supervised learning
- dynamic programming
- optimal control
- learning process
- information systems
- partially observable
- action space
- reinforcement learning methods
- perceptual aliasing