RESEARCH PAPERYear 2022

Temporal Difference Learning for Model Predictive Control

Nicklas A Hansen; Hao Su; Xiaolong Wang

Classification

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

Category review. TD-MPC establishes a pre-2026 general integration of task-oriented latent dynamics, terminal value learning and model-predictive action optimization. It is a canonical foundation explicitly used in the manuscript WM/MBRL thread. 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{td_mpc,
  author       = {Nicklas Hansen and
                  Hao Su and
                  Xiaolong Wang},
  title        = {Temporal Difference Learning for Model Predictive Control},
  booktitle    = {ICML},
  pages        = {8387--8406},
  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