dreamer_v3_50m(pretrained: bool = False, overrides: object = {})Construct the middle rung — no objectives, just the model.
A model dimension of 512: a 4096-unit recurrence, 32 classes per
latent, 32 channels at the first convolution. These are the values
DreamerV3Config defaults to, so this rung and a bare
configuration are the same model.
Model Size
Parameters
pretrainedbool= FalseNo weights are published for this family; passing
True raises.**overridesobject= {}Optional
DreamerV3Config field overrides.Returns
DreamerV3ModelThe trunk at 50M parameters.
Notes
Reference: Hafner, Pasukonis, Ba, and Norouzi, "Mastering Diverse Domains through World Models", Nature 640 (2025), 647-653 (arXiv:2301.04104), Table 3.
Examples
>>> from lucid.models import dreamer_v3_50m
>>> model = dreamer_v3_50m(action_dim=6).eval()
>>> model.config.deter_size, model.config.discrete
(4096, 32)