A Deep Reinforcement Learning-Based Dynamic Computational Offloading Method for Cloud Robotics.
Manoj PenmetchaByung-Cheol MinPublished in: IEEE Access (2021)
Keyphrases
- synthetic data
- reinforcement learning
- high accuracy
- preprocessing
- classification method
- detection method
- experimental evaluation
- cost function
- dynamic programming
- computational cost
- high precision
- objective function
- optimization method
- optimization algorithm
- pairwise
- image segmentation
- learning algorithm
- segmentation method
- mobile robot
- theoretical analysis
- dynamic environments
- unsupervised learning
- data management
- edge detection
- neural network
- lower bound
- training data
- similarity measure
- face recognition
- machine learning