RESEARCH PAPERYear 2019

Learning Latent Dynamics for Planning from Pixels

Danijar Hafner; Timothy Lillicrap; Ian Fischer; Ruben Villegas; David Ha; Honglak Lee; James Davidson

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. PlaNet introduces the pre-2026 recurrent state-space model and online latent-space CEM planning from pixels. The manuscript explicitly uses its stochastic/deterministic dynamics construction as a world-model foundation. 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{hafner2019learning,
  author       = {Danijar Hafner and
                  Timothy P. Lillicrap and
                  Ian Fischer and
                  Ruben Villegas and
                  David Ha and
                  Honglak Lee and
                  James Davidson},
  title        = {Learning Latent Dynamics for Planning from Pixels},
  booktitle    = {ICML},
  pages        = {2555--2565},
  year         = {2019},
}

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