Q-learning efficiency

Q-Learning Useful Machine Learning algorithm

By definition Q-Learning works by learning an action-value function that ultimately gives the expected utility of taking a given action in a given state and following the optimal policy thereafter. A policy is a rule that the agent follows in selecting actions, given the state it is in.

This might sounds very “crazy” but actually this is an awesome model/algorithm to find the best way to go from point A to point B and even the model can learn it and found the best way itself very quickly. Q-Learning used in every day world for instance to find the best fly connections or find the path on a map for you when you get a direction. But this is much more like these because Machine Learning allows to lear and getting better and better to provide more quality information.

Q-Learning has a quick learning curve and can provide quality information very quickly.
Wikipedia: https://en.wikipedia.org/wiki/Q-learning

Efficiency of Q-Learning

To compare Q-Learning to typical neural networks it has much better results at the moment. The blue line represents the Q-Learning algorithm to compare 1 and 2 layer neural networks what are much better then just randomly try to figure out the best “to do”.

FUN part

Q-Learning is typically very good in arcade games as well. To use machine learning to play a game like chess, tick-tack-toe or Pac-Man Q-Learning is a very efficient model and very efficient.

[siteorigin_widget class=”SiteOrigin_Widget_Image_Widget”][/siteorigin_widget]