Dreamer 4

Hafner and colleagues have released [Dreamer 4](https://arxiv.org/abs/2509.24527). This seem to be quite a departure from Dreamer V3 as D4 is demonstrated on learning strictly from an offline dataset with a world model based on diffusion, among other significant changes.

Opening this issues as a point of discussion and to help scaffold an eventual implementation.

No files, tests, or entry points are named. Start by reading the linked Dreamer 4 paper and comparing its offline, diffusion-based world model with the repository's current Dreamer V3-related scope; done first means agreeing on an implementation plan and boundaries.

Written by the indexing model from the issue text.