Editing Q-learning (section)

== Limitations ==
The standard Q-learning algorithm (using a <math>Q</math> table) applies only to discrete action and state spaces. [[Discretization]] of these values leads to inefficient learning, largely due to the [[curse of dimensionality]]. However, there are adaptations of Q-learning that attempt to solve this problem such as Wire-fitted Neural Network Q-Learning.<ref>{{Cite web|last1=Gaskett|first1=Chris|last2=Wettergreen|first2=David|last3=Zelinsky|first3=Alexander|date=1999|title=Q-Learning in Continuous State and Action Spaces|url=http://users.cecs.anu.edu.au/~rsl/rsl_papers/99ai.kambara.pdf}}</ref>