Q-learning for Statically Scheduling DAGs.
Julius RoederBenjamin RouxelClemens GrelckPublished in: IEEE BigData (2020)
Keyphrases
- reinforcement learning
- directed acyclic graph
- scheduling problem
- scheduling algorithm
- multi agent
- cooperative
- function approximation
- learning algorithm
- state space
- dynamic scheduling
- round robin
- flexible manufacturing systems
- belief networks
- resource constraints
- model free
- learning rate
- dynamic programming
- control system
- machine learning
- action selection
- equivalence classes
- parallel processors
- temporal difference learning