A novel framework is proposed that integrates MPC with RL in a sequence decision-making framework and leverages a curvature-aware optimization to efficiently tackle non-convex loss landscapes and achieves higher returns and faster convergence.
Abstract
Decision-making in high-dimensional, nonlinear systems remains a central challenge in robotics. While model-based methods like Model Predictive Control (MPC) offer sample efficiency and interpretability, their performance degrades when the dynamics model is inaccurate or long-horizon predictions are required. Conversely, model-free reinforcement learning (RL) learns policies directly from interaction but suffers from high sample complexity and unstable optimization. Recent advances in sequence modeling have inspired transformer-based decision-making frameworks that can unify MPC and RL, but their training typically faces significant optimization challenges due to highly non-convex loss landscapes. In this work, we propose a novel framework that integrates MPC with RL in a sequence decision-making framework and leverages a curvature-aware optimization to efficiently tackle non-convex loss landscapes. MPC provides predictions of locally optimal trajectories that guide the decision transformer, removing the need for extensive offline pretraining. To address the slow and unstable convergence of traditional optimizers, we train the policy in a Riemannian parameter space using an efficient Riemannian (curvature-aware) method, leading to faster and more robust optimization. We evaluate our framework on high-dimensional quadruped control tasks and demonstrate consistent improvements over strong baselines, including TRPO, SAC, and Online Decision Transformer, achieving higher returns and faster convergence.
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) uses low-variance solver gradients from differentiable MPC to optimize surrogate losses on predicted trajectories but can be biased under model mismatch. We propose Solver-Gradient Guided Reinforcement Learning (SG-RL), a solver-sensitivity augmentation for RL-based online MPC cost-weight adaptation. SG-RL keeps sampled closed-loop return as the objective and uses bounded solver-derived gradients as auxiliary guidance to improve stability and sample efficiency. We instantiate SG-RL in Proximal Policy Optimization (PPO) with four modular algorithms that inject solver-gradient guidance into actor-update scaling, policy loss, advantage estimation, and value-function learning. On two full-scale autonomous racing platforms with intentional model mismatch, SG-RL reaches PPO's best closed-loop return with up to 70.6% fewer samples, outperforms GB-PL baselines by at least 54% in closed-loop return, and generalizes zero-shot to unseen environments.
Baha Zarrouki, Arslan Thobani, Jasper Hoffmann et al.· 0 citations
PEARL employs an actor-adjoint algorithm that leverages automatic differentiation to compute policy gradients over short horizons and adjoint-based sensitivities of future returns approximated via neural networks, significantly reducing the number of environment interactions, while mitigating long-term gradient instabilities.
Real-time control often sits between two limiting regimes. Predictive optimization and model-based control are powerful when dynamics, parameters, objectives, and online planning models are specified; reinforcement learning can relax this requirement, but must infer long-horizon value signals from sequential data and interaction, making training slow, high-variance, and hard to scale in large action spaces. This middle regime is common in systems including autonomous driving, warehouse robotics, traffic control, and delivery drones: partial geometry, physics, rules, or constraints are known, yet the local direction of task progress remains uncertain. Geometric Distributional Control (GDC) is designed for this partial-knowledge setting. It factorizes control into feasibility and progress: known geometry, rules, constraints, and response maps define an executable scaffold, while progress-weighted feasible data learns the missing directional signal on that scaffold. The learned score acts as a Bellman-like local value-gradient, selecting actions that make progress without requiring global Bellman recursion, a fully specified planner, or a black-box policy that absorbs both feasibility and preference. This knowledge can be lightweight and partial, such as simple dynamics, safety filters, local maps, constraint projectors, or lower-level response maps; it need not encode full dynamics or a long-horizon objective. Offline, GDC fits a progress-tilted distribution from short known-feasible snippets with weak signed progress certificates. Online, its score is projected through the scaffold and applied in receding-horizon feedback. We prove that this score descends a data-induced soft progress value and validate GDC on structured multilevel optimization and SUMO route-progress driving, where it improves over known-only solvers and learning baselines while preserving scaffold-enforced feasibility.
Optimal decision-making under uncertainty is a shared challenge across modern chemical, manufacturing, and energy systems that increasingly demand safe, data-driven autonomy. This talk revisits optimal control through the lens of the Bellman equation, emphasizing how optimal control theory and reinforcement learning have developed complementary, yet largely disconnected, perspectives on global optimality. In one view, central to reinforcement learning, the Bellman equation defines a global optimality condition that guides iterative policy learning from interacting with the system, but typically yields opaque control laws that are difficult to interpret, and deploy in safety-critical settings. In another view, widely adopted in model predictive control (MPC), the Bellman equation underpins tractable finite-horizon optimizations that deliver interpretable, constraint-aware, and modular local controllers, yet without explicit guarantees on alignment with global optimality. Building on these ideas, we introduce a local–global paradigm that treats MPC and related optimization-based controllers as structured function approximators designed to approximately satisfy the global Bellman optimality condition. We discuss algorithmic strategies for learning interpretable local decision makers whose adaptation is guided by Bellman residuals, along with the benefits and practical challenges that arise in terms of stability, constraint satisfaction, and sample efficiency. These concepts are illustrated through case studies that unify reinforcement learning and MPC for safe, high-performance control in complex, uncertain dynamical systems. The talk concludes by outlining open problems and research opportunities in learning interpretable control policies that achieve globally optimal performance while retaining the transparency and reliability required for real-world process control and optimization applications.
A. Mesbah· Proceedings of the 3rd Found...· 0 citations
Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneous robots, sparse workspaces, simplified geometry, offline computation, or handcrafted parameters to make the problem tractable, which limits their deployment in dense crowd scenarios. Toward this end, we propose Shape-Aware Reinforcement Learned Model Predictive Control (SRL-MPC), a method for safe, efficient, and adaptive navigation in crowds with heterogeneous shapes without geometry simplification. To encode shape-aware safety, we formulate high-order control barrier function (HOCBF) constraints from geometric separation features (GSFs) based on support function transformation. A reinforcement learning (RL) framework then learns a neural policy that reads GSFs and outputs real-time MPC parameter updates, enabling the MPC solver to adapt to neighboring crowd geometries. The key advantage of SRL-MPC is that it preserves the safety structure and generalizability of MPC while integrating the adaptability and intelligence of RL. Experiments in randomized crowd scenarios with arbitrary shaped robot fleets demonstrate the effectiveness, scalability, and robustness of SRL-MPC. The results show that SRL-MPC substantially outperforms representative baselines in safety and adaptability. Project website: https://hanruihua.github.io/srl_mpc_project/
Applying policy optimization to Model Predictive Control (MPC) yields high-performance and reliable controllers. However, the resulting controllers often overfit their training conditions and suffer significant performance degradation in unseen tasks. We propose a novel framework combining policy optimization with meta-learning to train highly adaptable MPC controllers. Our approach enables rapid adaptation to unseen tasks, maintaining high performance at a fraction of the computational cost required for full retraining. Furthermore, we integrate system identification into the pipeline to continuously refine both the MPC hyperparameters and the underlying predictive models. We validate our proposed methodology on a Ball-on-Plate system, demonstrating superior adaptability across various parameterized trajectory-tracking tasks.
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
