Saved in:
Bibliographic Details
Main Authors: Zhou, Guangyao, Swaminathan, Sivaramakrishnan, Raju, Rajkumar Vasudeva, Guntupalli, J. Swaroop, Lehrach, Wolfgang, Ortiz, Joseph, Dedieu, Antoine, Lázaro-Gredilla, Miguel, Murphy, Kevin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.05364
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.