Handle for 2D/3D observations that are images

I was also about to open an issue regarding Dreamer on feature-vector based (partially observable) environments where no Cnn is needed (and as a matter of fact, to also handle gridworlds where the observation space is also with matrices, except non-RGB, for example with 1's where the agents are and 0's otherwise).

What would be necessary to adapt from the code? I would be willing to help you guys!

_Originally posted by @jmribeiro in https://github.com/Eclectic-Sheep/sheeprl/issues/229#issuecomment-1991783930_

No files, tests, or entry points are named. Review how Dreamer currently handles image observations, then determine the changes needed to support feature-vector environments and non-RGB matrix or gridworld observations; done means these observation types work without requiring a CNN.

Written by the indexing model from the issue text.