Diffusion Model Predictive Control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910963644497920 |
|---|---|
| author | Zhou, Guangyao Swaminathan, Sivaramakrishnan Raju, Rajkumar Vasudeva Guntupalli, J. Swaroop Lehrach, Wolfgang Ortiz, Joseph Dedieu, Antoine Lázaro-Gredilla, Miguel Murphy, Kevin |
| author_facet | Zhou, Guangyao Swaminathan, Sivaramakrishnan Raju, Rajkumar Vasudeva Guntupalli, J. Swaroop Lehrach, Wolfgang Ortiz, Joseph Dedieu, Antoine Lázaro-Gredilla, Miguel Murphy, Kevin |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05364 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion Model Predictive Control Zhou, Guangyao Swaminathan, Sivaramakrishnan Raju, Rajkumar Vasudeva Guntupalli, J. Swaroop Lehrach, Wolfgang Ortiz, Joseph Dedieu, Antoine Lázaro-Gredilla, Miguel Murphy, Kevin Machine Learning Artificial Intelligence 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. |
| title | Diffusion Model Predictive Control |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.05364 |