Online Reinforcement Learning for Self-adaptive Information Systems.
Alexander PalmAndreas MetzgerKlaus PohlPublished in: CAiSE (2020)
Keyphrases
- information systems
- reinforcement learning
- information technology
- online learning
- state space
- dynamic programming
- function approximation
- reinforcement learning algorithms
- online environment
- real time
- learning problems
- dynamical systems
- markov decision processes
- computer systems
- supervised learning
- website
- markov decision process
- learning algorithm