Uncertainty propagation for quality assurance in Reinforcement Learning.
Daniel SchneegaßSteffen UdluftThomas MartinetzPublished in: IJCNN (2008)
Keyphrases
- quality assurance
- reinforcement learning
- quality control
- function approximation
- monitoring system
- quality assessment
- optimal policy
- learning algorithm
- partial observability
- state space
- software development
- white box testing
- software quality
- software testing
- model free
- markov decision processes
- multi agent
- machine learning
- user interface
- decision making
- scripting languages