| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Files spread between Dropbox, Google Drive, Gmail, Slack, and more? Dokkio, a new product from the PBworks team, integrates and organizes them for you. Try it for free today.

View
 

RL = Q-learning or perhaps TD

Page history last edited by Satinder Singh 10 years, 11 months ago

The ambition of this page is to discuss and (hopefully dispel) the myth that RL is Q-learning (or perhaps TD).


Fortunately, this myth may well by dying a natural death. The most damaging form of this myth restricts RL to the simplest of RL methods: Q-learning and TD(lambda) with lookup tables or at most linear function approximators.

A casual perusal of the Algorithms of RL page will remind the viewer that there are a variety of different RL algorithms that explore the rich and multidimensional space of algorithm dimensions.

 

Comments (0)

You don't have permission to comment on this page.