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.