用离线数据训练模型，生成既符合数据又接近最优的轨迹。
Receding-Horizon Control via Drifting Models
- 结合漂移生成模型与滚动时域规划，从离线数据中学习轨迹分布。
- 在不依赖仿真模型的前提下，生成近似最优轨迹，且推理效率高。
- 适合缺乏动态模型但有轨迹数据的强化学习与控制场景。
我们研究在系统动态未知且无法通过代理模型模拟轨迹的场景下的轨迹优化问题。当存在离线轨迹数据集时，代理可直接通过分布匹配学习轨迹生成器，但此类方法仅能恢复数据中的行为分布，通常无法最小化目标代价。本文提出漂移MPC（Drifting MPC），一种结合漂移生成模型与滚动时域规划的离线轨迹优化框架。其目标是从离线轨迹数据中学习一个条件轨迹分布，该分布既由数据支持，又偏向于最优计划。我们证明，漂移MPC学习到的分布是权衡最优性与与离线先验接近程度的唯一解。实验表明，漂移MPC可在不依赖仿真模型的前提下生成近似最优轨迹，同时保持漂移模型的一步推理效率，并显著减少生成时间，相比扩散基线大幅降低耗时。
原文摘要 · Abstract (English)
We study the problem of trajectory optimization in settings where the system dynamics are unknown and it is not possible to simulate trajectories through a surrogate model. When an offline dataset of trajectories is available, an agent could directly learn a trajectory generator by distribution matching. However, this approach only recovers the behavior distribution in the dataset, and does not in general produce a model that minimizes a desired cost criterion. In this work, we propose Drifting MPC, an offline trajectory optimization framework that combines drifting generative models with receding-horizon planning under unknown dynamics. The goal of Drifting MPC is to learn, from an offline dataset of trajectories, a conditional distribution over trajectories that is both supported by the data and biased toward optimal plans. We show that the resulting distribution learned by Drifting MPC is the unique solution of an objective that trades off optimality with closeness to the offline prior. Empirically, we show that Drifting MPC can generate near-optimal trajectories while retaining the one-step inference efficiency of drifting models and substantially reducing generation time relative to diffusion-based baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。