Factored Reinforcement Learning for Auto-scaling in Tandem Queues.
Thomas TournaireYue JinArmen AghasaryanHind Castel-TalebEmmanuel HyonPublished in: NOMS (2022)
Keyphrases
- reinforcement learning
- state space
- factored markov decision processes
- function approximation
- reinforcement learning algorithms
- processor sharing
- waiting times
- learning algorithm
- dynamic programming
- control problems
- queueing networks
- temporal difference
- model free
- markov decision problems
- optimal control
- optimal policy
- learning problems
- learning process
- machine learning
- retrial queue
- service rates
- single server
- data structure
- action space
- finite capacity
- multi agent
- priority queue
- reinforcement learning methods
- partially observable markov decision processes
- least squares
- supervised learning
- linear programming
- data sets
- queue length