RESEARCH PAPERYear 2023

DayDreamer: World Models for Physical Robot Learning

Philipp Wu; Alejandro Escontrela; Danijar Hafner; Pieter Abbeel; Ken Goldberg

Classification

Major category: Foundational work
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Classical world models & model-based RL
Source review status: Verified from primary sources

Category review. DayDreamer establishes pre-2026 physical-robot application of latent world-model actor-critic learning across several embodiments. Its dynamics/imagination/actor loop is a historical MBRL predecessor, not joint future/action prediction. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@inproceedings{daydreamer,
  author       = {Philipp Wu and
                  Alejandro Escontrela and
                  Danijar Hafner and
                  Pieter Abbeel and
                  Ken Goldberg},
  title        = {DayDreamer: World Models for Physical Robot Learning},
  booktitle    = {CoRL},
  pages        = {2226--2240},
  year         = {2022},
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Critique of World Model

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Mean Flows for One-step Generative Modeling