arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.01477cs.LGcs.SYeess.SY
收藏

软MPCritic: amortized模型预测价值迭代

Soft MPCritic: Value-Based Reinforcement Learning for Non-Differentiable Predictive Control

Thomas Banker, Nathan P. Lawrence, Ali Mesbah

AI总结:

软MPCritic结合了强化学习与模型预测控制,通过价值空间学习和基于样本的规划实现高效控制,保留了规划 horizon 的有效性。

摘要:

强化学习(RL)和模型预测控制(MPC)具有互补优势,但大规模结合仍具计算挑战。我们提出了soft MPCritic,一个RL-MPC框架,通过在(软)价值空间中学习,并利用基于样本的规划进行在线控制和价值目标生成。soft MPCritic通过模型预测路径积分控制(MPPI)实例化MPC,并通过拟合价值迭代训练终端Q函数,使学习的价值函数与规划器对齐,并隐式扩展有效规划 horizon。我们引入了amortized warm-start策略,在计算批量MPPI基于价值目标时重用在线观测中的计划开环动作序列。这使soft MPCritic在计算上可行,同时保持了解质量。soft MPCritic通过一组训练用于下一步预测准确性的动态模型进行基于场景的规划。这些成分使soft MPCritic能够在经典和复杂控制任务上通过鲁棒、短 horizon 的规划有效学习。这些结果确立了soft MPCritic作为在政策提取和直接、长 horizon 规划可能失败的场景中合成MPC策略的实用且可扩展的蓝图。

英文摘要:

Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet existing MPC-RL frameworks commonly rely on gradient-based optimization and therefore cannot handle the non-differentiable dynamics and objectives common in RL. We propose Soft MPCritic, an MPC-RL framework that learns a soft value function and uses sampling-based planning both for online control and for generating value targets. Specifically, Soft MPCritic instantiates MPC with model predictive path integral control (MPPI) and learns a terminal Q-function through fitted value iteration. Because the value targets are computed by the same planner used for control, the learned value function is aligned with the planner and implicitly extends its effective horizon. To keep target generation tractable, we introduce an amortized warm-start strategy that reuses the open-loop action sequences planned during online control to initialize batched MPPI computations of value targets, reducing computational cost without sacrificing solution quality. For robustness to model error, Soft MPCritic plans over scenarios drawn from an ensemble of dynamics models trained for next-step prediction. On both classical and constrained control tasks, Soft MPCritic learns effective policies with non-differentiable objectives, particularly where finite-horizon MPPI alone falls short. Soft MPCritic thus offers a practical blueprint for synthesizing MPC policies directly from black-box objectives, without differentiable surrogates.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑