We propose Diffusion Model Predictive Control (D-MPC), a novel MPC approach that learns a multi-step action proposal and a multi-step dynamics model, both using diffusion models, and combines them for use in online MPC. On the popular D4RL benchmark, we show performance that is significantly better than existing model-based offline planning methods using MPC (e.g. MBOP) and competitive with state-of-the-art (SOTA) model-based and model-free reinforcement learning methods. We additionally illustrate D-MPC's ability to optimize novel reward functions at run time and adapt to novel dynamics, and highlight its advantages compared to existing diffusion-based planning baselines.
@article{arxiv.2410.05364,
title = {Diffusion Model Predictive Control},
author = {Guangyao Zhou and Sivaramakrishnan Swaminathan and Rajkumar Vasudeva Raju and J. Swaroop Guntupalli and Wolfgang Lehrach and Joseph Ortiz and Antoine Dedieu and Miguel Lázaro-Gredilla and Kevin Murphy},
journal= {arXiv preprint arXiv:2410.05364},
year = {2025}
}