papers

Publications (49)

cs.LG2026

Incremental Gauss-Newton Descent for Machine Learning

Mikalai Korbit, Mario Zanon

Stochastic gradient updates are widely used for their efficiency and scalability, but their effective step sizes can depend strongly on feature scaling and local model sensitivity.…

math.OC2026

On Two-Player Scalar Discrete-Time Linear Quadratic Games

Chiara Cavalagli, Alberto Bemporad, Mario Zanon

For the characterization of Feedback Nash Equilibria (FNE) in linear quadratic games, this paper provides a detailed analysis of the discrete-time discounted coupled best-response…

math.OC2017

Optimal Scheduling of Downlink Communication for a Multi-Agent System with a Central Observation Post

Mario Zanon, Themistoklis Charalambous, Henk Wymeersch +1

In this paper, we consider a set of agents, which may receive an observation of their state by a central observa- tion post via a shared wireless network. The aim of this work is t…

eess.SY2021

Data-driven synthesis of Robust Invariant Sets and Controllers

Sampath Kumar Mulagaleti, Alberto Bemporad, Mario Zanon

This paper presents a method to identify an uncertain linear time-invariant (LTI) prediction model for tube-based Robust Model Predictive Control (RMPC). The uncertain model is det…

eess.SY2020

Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?

Sebastien Gros, Mario Zanon, Alberto Bemporad

For all its successes, Reinforcement Learning (RL) still struggles to deliver formal guarantees on the closed-loop behavior of the learned policy. Among other things, guaranteeing…

math.OC2026

Rethinking Strict Dissipativity for Economic MPC

Mario Zanon

Stability of economic model predictive control can be proven under the assumption that a strict dissipativity condition holds. This assumption has a clear interpretation in terms o…

math.OC2025

Stabilization of Strictly Pre-Dissipative Receding Horizon Linear Quadratic Control by Terminal Costs

Mario Zanon, Lars Grüne

Asymptotic stability in receding horizon control is obtained under a strict pre-dissipativity assumption, in the presence of suitable state constraints. In this paper we analyze ho…

eess.SY2022

Economic MPC of Markov Decision Processes: Dissipativity in Undiscounted Infinite-Horizon Optimal Control

Sébastien Gros, Mario Zanon

Economic Model Predictive Control (MPC) dissipativity theory is central to discussing the stability of policies resulting from minimizing economic stage costs. In its current form,…

eess.SY2021

Constrained Controller and Observer Design by Inverse Optimality

Mario Zanon, Alberto Bemporad

Model Predictive Control (MPC) is often tuned by trial and error. When a baseline linear controller exists that is already well tuned in the absence of constraints and MPC is intro…

eess.SY2019

Towards Safe Reinforcement Learning Using NMPC and Policy Gradients: Part II - Deterministic Case

Sebastien Gros, Mario Zanon

In this paper, we present a methodology to deploy the deterministic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametri…

eess.SY2019

Real-Time Constrained Trajectory Planning and Vehicle Control for Proactive Autonomous Driving With Road Users

Ivo Batkovic, Mario Zanon, Mohammad Ali +1

For motion planning and control of autonomous vehicles to be proactive and safe, pedestrians' and other road users' motions must be considered. In this paper, we present a vehicle…

math.OC2024

Optimality Conditions for Model Predictive Control: Rethinking Predictive Model Design

Akhil S Anand, Arash Bahari Kordabad, Mario Zanon +1

Optimality is a critical aspect of Model Predictive Control (MPC), especially in economic MPC. However, achieving optimality in MPC presents significant challenges, and may even be…

eess.SY2022

Model Predictive Control Tuning by Monte Carlo Simulation and Controller Matching

Morten Ryberg Wahlgreen, John Bagterp Jørgensen, Mario Zanon

This paper presents a systematic method for the selection of the Model Predictive Control (MPC) stage cost. We match the MPC feedback law to a proportional-integral (PI) controller…

eess.SY2021

Safe Trajectory Tracking in Uncertain Environments

Ivo Batkovic, Mohammad Ali, Paolo Falcone +1

In Model Predictive Control (MPC) formulations of trajectory tracking problems, infeasible reference trajectories and a-priori unknown constraints can lead to cumbersome designs, a…

math.OC2017

A Feasibility-Enforcing Primal-Decomposition SQP Algorithm for Optimal Vehicle Coordination

Mario Zanon, Robert Hult, Sebastien Gros +1

In this paper we consider the problem of coordinating autonomous vehicles approaching an intersection. We cast the problem in the distributed optimisation framework and propose an…

eess.SY2026

Active Learning MPC Objective Functions from Preferences

Hasna El Hasnaouy, Pablo Krupa, Mario Zanon +1

Designing the objective function in Model Predictive Control (MPC) is challenging when performance assessment criteria are available only from human judgment. We adopt a preference…

cs.RO2023

Experimental Validation of Safe MPC for Autonomous Driving in Uncertain Environments

Ivo Batkovic, Ankit Gupta, Mario Zanon +1

The full deployment of autonomous driving systems on a worldwide scale requires that the self-driving vehicle be operated in a provably safe manner, i.e., the vehicle must be able…

eess.SY2020

Reinforcement Learning for Mixed-Integer Problems Based on MPC

Sebastien Gros, Mario Zanon

Model Predictive Control has been recently proposed as policy approximation for Reinforcement Learning, offering a path towards safe and explainable Reinforcement Learning. This ap…

eess.SY2021

A Semi-Distributed Interior Point Algorithm for Optimal Coordination of Automated Vehicles at Intersections

Robert Hult, Mario Zanon, Sebastien Gros +1

In this paper, we consider the optimal coordination of automated vehicles at intersections under fixed crossing orders. We formulate the problem using direct optimal control and ex…

eess.SY2020

A Gauss-Newton-Like Hessian Approximation for Economic NMPC

Mario Zanon

Economic Model Predictive Control (EMPC) has recently become popular because of its ability to control constrained nonlinear systems while explicitly optimizing a prescribed perfor…

eess.SY2018

A Computationally Efficient Model for Pedestrian Motion Prediction

Ivo Batkovic, Mario Zanon, Nils Lubbe +1

We present a mathematical model to predict pedestrian motion over a finite horizon, intended for use in collision avoidance algorithms for autonomous driving. The model is based on…

eess.SY2023

Computation of safe disturbance sets using implicit RPI sets

Sampath Kumar Mulagaleti, Alberto Bemporad, Mario Zanon

Given a stable linear time-invariant (LTI) system subject to output constraints, we present a method to compute a set of disturbances such that the reachable set of outputs matches…

math.OC2025

Stabilization of strictly pre-dissipative nonlinear receding horizon control by terminal costs

Lars Grüne, Mario Zanon

It is known that receding horizon control with a strictly pre-dissipative optimal control problem yields a practically asymptotically stable closed loop when suitable state constra…

eess.SY2019

Practical Reinforcement Learning of Stabilizing Economic MPC

Mario Zanon, Sébastien Gros, Alberto Bemporad

Reinforcement Learning (RL) has demonstrated a huge potential in learning optimal policies without any prior knowledge of the process to be controlled. Model Predictive Control (MP…

eess.SY2020

Robust Control Invariance and Communication Scheduling in Lossy Wireless Networked Control Systems

Masoud Bahraini, Mario Zanon, Paolo Falcone +1

In Networked Control Systems (NCS) impairments of the communication channel can be disruptive to stability and performance. In this paper, we consider the problem of scheduling the…

eess.SY2023

Equivalence of Optimality Criteria for Markov Decision Process and Model Predictive Control

Arash Bahari Kordabad, Mario Zanon, Sebastien Gros

This paper shows that the optimal policy and value functions of a Markov Decision Process (MDP), either discounted or not, can be captured by a finite-horizon undiscounted Optimal…

eess.SY2020

Safe Reinforcement Learning Using Robust MPC

Mario Zanon, Sébastien Gros

Reinforcement Learning (RL) has recently impressed the world with stunning results in various applications. While the potential of RL is now well-established, many critical aspects…

eess.SY2026

On Piecewise Quadratic Terminal Costs for MPC

Sampath Kumar Mulagaleti, Boris Houska, Mario Zanon +1

This paper presents a novel approach to synthesize stabilizing termi- nal ingredients for linear model predictive control (MPC) schemes, with the aim of increasing the region of at…

eess.SY2025

Economic Linear Quadratic MPC With Non-Unique Optimal Solutions

Mario Zanon

Asymptotic stability in economic receding horizon control can be obtained under a strict dissipativity assumption, related to positive-definiteness of a so-called rotated cost, and…

math.OC2021

Computation of Input Disturbance Sets for Constrained Output Reachability

Sampath Kumar Mulagaleti, Alberto Bemporad, Mario Zanon

Linear models with additive unknown-but-bounded input disturbances are extensively used to model uncertainty in robust control systems design. Typically, the disturbance set is eit…

cs.LG2026

Fast Gauss-Newton for Multiclass Cross-Entropy

Mikalai Korbit, Mario Zanon

In multiclass softmax cross-entropy, the full generalized Gauss-Newton (GGN) curvature couples all output logits through the softmax covariance, making curvature-vector products ha…

cs.LG2022

Learning for MPC with Stability & Safety Guarantees

Sébastien Gros, Mario Zanon

The combination of learning methods with Model Predictive Control (MPC) has attracted a significant amount of attention in the recent literature. The hope of this combination is to…

eess.SY2021

Model Predictive Control with Infeasible Reference Trajectories

Ivo Batkovic, Mohammad Ali, Paolo Falcone +1

Model Predictive Control (MPC) formulations are typically built on the requirement that a feasible reference trajectory is available. In practical settings, however, references tha…

eess.SY2020

Primal or Dual Terminal Constraints in Economic MPC? -- Comparison and Insights

Timm Faulwasser, Mario Zanon

This chapter compares different formulations for Economic nonlinear Model Predictive Control (EMPC) which are all based on an established dissipativity assumption on the underlying…

eess.SY2019

Towards Safe Reinforcement Learning Using NMPC and Policy Gradients: Part I - Stochastic case

Sebastien Gros, Mario Zanon

We present a methodology to deploy the stochastic policy gradient method, using actor-critic techniques, when the optimal policy is approximated using a parametric optimization pro…

eess.SY2024

Optimization-based Heuristic for Vehicle Dynamic Coordination in Mixed Traffic Intersections

Muhammad Faris, Mario Zanon, Paolo Falcone

In this paper, we address a coordination problem for connected and autonomous vehicles (CAVs) in mixed traffic settings with human-driven vehicles (HDVs). The main objective is to…

eess.SY2023

Performance Quantification of a Nonlinear Model Predictive Controller by Parallel Monte Carlo Simulations of a Closed-loop System

Morten Wahlgreen Kaysfeld, Mario Zanon, John Bagterp Jørgensen

This paper presents a parallel Monte Carlo simulation based performance quantification method for nonlinear model predictive control (NMPC) in closed-loop. The method provides dist…

eess.SY2020

Reinforcement Learning Based on Real-Time Iteration NMPC

Mario Zanon, Vyacheslav Kungurtsev, Sébastien Gros

Reinforcement Learning (RL) has proven a stunning ability to learn optimal policies from data without any prior knowledge on the process. The main drawback of RL is that it is typi…

eess.SY2026

Characterization and Computation of Feedback Nash Equilibria in Scalar Discounted N-Player Linear Quadratic Games

Chiara Cavalagli, Alberto Bemporad, Mario Zanon

This paper studies feedback Nash equilibria (FNE) in scalar discounted linear quadratic (LQ) games with players. By explicitly incorporating the discount factor, we show that f…

eess.SY2025

Learning disturbance models for offset-free reference tracking

Pablo Krupa, Mario Zanon, Alberto Bemporad

This work presents a nonlinear control framework that guarantees asymptotic offset-free tracking of generic reference trajectories by learning a nonlinear disturbance model, which…

eess.SY2025

Learning the MPC objective function from human preferences

Pablo Krupa, Hasna El Hasnaouy, Mario Zanon +1

In Model Predictive Control (MPC), the objective function plays a central role in determining the closed-loop behavior of the system, and must therefore be designed to achieve the…

eess.SY2022

A New Dissipativity Condition for Asymptotic Stability of Discounted Economic MPC

Mario Zanon, Sébastien Gros

Economic Model Predictive Control has recently gained popularity due to its ability to directly optimize a given performance criterion, while enforcing constraint satisfaction for…

math.OC2019

A Parallel Decomposition Scheme for Solving Long-Horizon Optimal Control Problems

Sungho Shin, Timm Faulwasser, Mario Zanon +1

We present a temporal decomposition scheme for solving long-horizon optimal control problems. In the proposed scheme, the time domain is decomposed into a set of subdomains with pa…

cs.LG2026

Second-Order, First-Class: A Composable Stack for Curvature-Aware Training

Mikalai Korbit, Mario Zanon

Second-order methods promise improved stability and faster convergence, yet they remain underused due to implementation overhead, tuning brittleness, and the lack of composable API…

eess.SY2019

Data-driven Economic NMPC using Reinforcement Learning

Sébastien Gros, Mario Zanon

Reinforcement Learning (RL) is a powerful tool to perform data-driven optimal control without relying on a model of the system. However, RL struggles to provide hard guarantees on…

cs.LG2025

Exact Gauss-Newton Optimization for Training Deep Neural Networks

Mikalai Korbit, Adeyemi D. Adeoye, Alberto Bemporad +1

We present Exact Gauss-Newton (EGN), a stochastic second-order optimization algorithm that combines the generalized Gauss-Newton (GN) Hessian approximation with low-rank linear alg…

cs.LG2021

Stability-Constrained Markov Decision Processes Using MPC

Mario Zanon, Sébastien Gros, Michele Palladino

In this paper, we consider solving discounted Markov Decision Processes (MDPs) under the constraint that the resulting policy is stabilizing. In practice MDPs are solved based on s…

cs.RO2021

Model Predictive Control with Environment Adaptation for Legged Locomotion

Niraj Rathod, Angelo Bratta, Michele Focchi +4

Re-planning in legged locomotion is crucial to track the desired user velocity while adapting to the terrain and rejecting external disturbances. In this work, we propose and test…

physics.data-an2021

Fast and scalable likelihood maximization for Exponential Random Graph Models with local constraints

Nicolò Vallarano, Matteo Bruno, Emiliano Marchese +5

Exponential Random Graph Models (ERGMs) have gained increasing popularity over the years. Rooted into statistical physics, the ERGMs framework has been successfully employed for re…