RESEARCH PAPERYear 2022

Rapid Exploration for Open-World Navigation with Latent Goal Models

Dhruv Shah; Benjamin Eysenbach; Nicholas Rhinehart; Sergey Levine

Classification

Major category: Foundational work
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Action policy foundations Theory & planning
Source review status: Verified from primary sources

Category review. RECON is an early goal-conditioned latent-action/navigation predecessor: action and temporal-distance decoding, latent subgoal sampling, and topological planning support open-world exploration. It provides the pre-2026 goal-policy/planning thread without claiming joint future-world/action generation. 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{recon,
  author       = {Dhruv Shah and
                  Benjamin Eysenbach and
                  Nicholas Rhinehart and
                  Sergey Levine},
  title        = {Rapid Exploration for Open-World Navigation with Latent Goal Models},
  booktitle    = {CoRL},
  pages        = {674--684},
  year         = {2021},

}

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