{"ID":2896468,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06625","arxiv_id":"2507.06625","title":"Q-Guided Stein Variational Model Predictive Control via RL-informed Policy Prior","abstract":"Model Predictive Control (MPC) enables reliable trajectory optimization under dynamics constraints, but often depends on accurate dynamics models and carefully hand-designed cost functions. Recent learning-based MPC methods aim to reduce these modeling and cost-design burdens by learning dynamics, priors, or value-related guidance signals. Yet many existing approaches still rely on deterministic gradient-based solvers (e.g., differentiable MPC) or parametric sampling-based updates (e.g., CEM/MPPI), which can lead to mode collapse and convergence to a single dominant solution. We propose Q-SVMPC, a Q-guided Stein variational MPC method with an RL-informed policy prior, which casts learning-based MPC as trajectory-level posterior inference and refines trajectory particles via SVGD under learned soft Q-value guidance to explicitly preserve diverse solutions. Experiments on navigation, robotic manipulation, and a real-world fruit-picking task show improved sample efficiency, stability, and robustness over MPC, model-free RL, and learning-based MPC baselines.","short_abstract":"Model Predictive Control (MPC) enables reliable trajectory optimization under dynamics constraints, but often depends on accurate dynamics models and carefully hand-designed cost functions. Recent learning-based MPC methods aim to reduce these modeling and cost-design burdens by learning dynamics, priors, or value-rela...","url_abs":"https://arxiv.org/abs/2507.06625","url_pdf":"https://arxiv.org/pdf/2507.06625v3","authors":"[\"Shizhe Cai\",\"Zeya Yin\",\"Jayadeep Jacob\",\"Fabio Ramos\"]","published":"2025-07-09T07:53:53Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}