Reinforcement learning of adaptive online rescheduling timing and computing time allocation.
Teemu J. IkonenKeijo HeljankoIiro HarjunkoskiPublished in: Comput. Chem. Eng. (2020)
Keyphrases
- reinforcement learning
- online learning
- limited capacity
- data sets
- function approximation
- machine learning
- multi agent
- state space
- dynamic allocation
- resource allocation
- learning capabilities
- allocation problems
- real time
- real robot
- adaptive control
- markov decision processes
- optimal policy
- supervised learning
- learning process