SOURCE-LINKED INTELLIGENCE

Accelerating Reinforcement Learning via MPC Solver-Gradient Guidance for Weights-varying MPC

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

In Model Predictive Control (MPC), cost-function weights shape closed-loop behavior, yet changing conditions often make fixed parametrizations suboptimal and motivate context-dependent online adaptation. Learning such policies is difficult because behavior depends implicitly on numerical MPC solutions, producing nonlinear, potentially nonsmooth, long-horizon dependencies on policy parameters. This creates a bias-variance tradeoff: Reinforcement Learning (RL) optimizes realized closed-loop return from environment samples but is sample-inefficient, whereas Gradient-Based Policy Learning (GB-PL)

Read original source ↗ Open in workspace

recordType

paper

region

Global