Good question.

I think it would depend on the nature of the temporal dependencies that need to be captured. If a couple frames capture of the dynamics of an environment, then just stacking them is probably the easier and more robust solution. If the dynamics might span more than just a few frames however, it becomes computationally more reasonable to use an RNN to learn those dependencies rather than stacking a dozen or more frames.

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

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