In most cases, the state will be from continuous spaces. Like for instance pixels from a computer game. Here you have an infinite amount of possibilities how pixels can be arranged. The action space that is continuous cannot be solved with DQN. Only if you have 1000000000 possible actions, you would need to have 1000000000 output neurons. So as you can imagine is quite computationally expensive.

Deep Learning & AI Software Developer | MSc. Physics | Educator|

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store