Online RL-based cloud autoscaling for scientific workflows: Evaluation of Q-Learning and SARSA.
Yisel GariElina PaciniLuciano RobinoCristian MateosDavid A. MongePublished in: Future Gener. Comput. Syst. (2024)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- scientific workflows
- temporal difference learning
- action selection
- rl algorithms
- model free
- state space
- learning algorithm
- multi agent
- policy iteration
- markov decision processes
- optimal control
- optimal policy
- cloud computing
- reinforcement learning methods
- dynamic programming
- temporal difference
- business processes
- function approximators
- data warehouse
- semantic annotation
- intelligent agents
- learning agent
- stochastic games
- sensor networks