Correcting flawed expert knowledge through reinforcement learning.
David O. AiheAvelino J. GonzalezPublished in: Expert Syst. Appl. (2015)
Keyphrases
- expert knowledge
- reinforcement learning
- expert systems
- learned knowledge
- domain knowledge
- knowledge engineering
- fuzzy logic
- bayesian networks
- function approximation
- domain experts
- state space
- knowledge base
- optimal policy
- knowledge elicitation
- markov decision processes
- prior knowledge
- supervised learning
- robotic control
- multi agent
- information systems
- model free
- real time
- active learning
- data mining
- optimal control
- temporal difference learning
- reinforcement learning algorithms
- reinforcement learning methods
- transition model
- knowledge based systems
- temporal difference
- action selection
- knowledge acquisition
- control system
- learning process
- data sets