Deep Reinforcement Learning Acceleration for Real-Time Edge Computing Mixed Integer Programming Problems.
Gerasimos GerogiannisMichael K. BirbasAimilios LeftheriotisEleftherios MylonasNikolaos TzanisAlexios N. BirbasPublished in: IEEE Access (2022)
Keyphrases
- mixed integer programming problems
- real time
- reinforcement learning
- robotic control
- edge detection
- low cost
- vision system
- function approximation
- multiscale
- control system
- learning algorithm
- action selection
- multiple scales
- real world
- state space
- machine learning
- markov decision processes
- edge information
- function approximators
- data sets