Search arXiv⌕ Search

arXiv subjects

Alberto Bemporad

Publications and source records attributed to Alberto Bemporad.

At least 19 recordsLinked to original sources

A Hierarchical Variational Inequality Approach to Generalized Nash Equilibrium Seeking with Nonlinear Shared Constraints

We study the computation of variational generalized Nash equilibria (v-GNE) in games with strongly monotone pseudo-gradients and nonlinear convex shared constraints. We show that the v-GNE problem is exactly equivalent to a hierarchical variational inequality, whose lower level is given by the gradient of a smooth convex penalty of the constraint violation over the local action sets. Building on this reformulation, we propose a hierarchical regularization scheme that operates entirely in the primal space and requires only projections onto the local action sets. In the centralized setting, we prove last-iterate squared distance convergence to the v-GNE with rate $O(1/t^{\scriptscriptstyle 2/3})$ under a local error bound condition, which holds, e.g., under Slater's condition, improved to $O(1/t)$ under a global error bound condition. We then extend the scheme to the partial-decision information setting, where the agents communicate over a network and maintain local estimates of the joint action. We derive a distributed algorithm with a constant stepsize operating in the primal space and converging to the v-GNE with rate $O(1/t)$.

math.OC↗

Stability Filters for Receding-Horizon Games

In receding-horizon games, self-interested players repeatedly solve a finite-horizon generalized Nash equilibrium problem (GNEP) and apply its first-stage actions. Ensuring stability of the resulting closed-loop system, however, is a challenging task that requires careful design of the players' strategies or additional constraints. We propose a stability filter that minimally modifies the variational equilibrium of the finite-horizon GNEP to enforce a prescribed decrease of a quadratic Lyapunov function. For receding-horizon games with linear dynamics, quadratic costs, and polyhedral coupling input constraints, whose associated GNEP is strongly monotone, we show that a filter always exists such that a closed-loop equilibrium exists, the filter is always feasible, does not intervene when the equilibrium already satisfies the decrease condition, and that renders the closed loop globally exponentially stable. Moreover, the filtered strategy is an $ε$-generalized Nash equilibrium, with $epsilon$ vanishing exponentially along closed-loop trajectories.

math.OC↗

Input Design for Angles-Only Initial Relative Orbit Determination Using Active Learning

Angles-only initial relative orbit determination (IROD) is a challenging estimation problem, as the lack of direct range information results in scale ambiguity and weak practical observability. To address these limitations, this paper introduces an input-design approach to angles-only IROD, in which excitation maneuvers are systematically designed within an active-learning framework. From a dual-control perspective, the resulting control inputs promote exploration of the output space to improve initial-state estimation while accounting for station-keeping requirements and control effort. Angular measurements collected under the resulting maneuver sequence are processed by a batch IROD algorithm extended to handle generic input sequences. A first-order analytical covariance matrix of the initial-state estimate is derived to quantify the uncertainty induced by measurement noise and to support the transition from batch estimation to sequential filtering. Numerical simulations and Monte Carlo sensitivity analyses show that the proposed input-design strategy improves initialization accuracy and conditioning compared with baseline excitation methods and supports autonomous rendezvous in the tested scenarios.

eess.SY↗

Manifold meta-learning for reduced-complexity neural system identification

System identification has greatly benefited from deep learning techniques, particularly for modeling complex, nonlinear dynamical systems with partially unknown physics where traditional approaches may not be feasible. However, deep learning models often require large datasets and significant computational resources for both training and inference due to their high-dimensional parameterizations. To address this challenge, we propose a meta-learning framework that discovers a low-dimensional manifold within the parameter space of an over-parameterized neural network architecture. This manifold is learned from an abundant meta-dataset of input-output sequences generated by a simulator of the class of systems of interest, and thereafter enables efficient model training while preserving the network's expressive power for the considered system class. Unlike bilevel meta-learning approaches, our method employs an auxiliary neural network to map datasets directly onto the learned manifold, eliminating the need for costly second-order gradient computations during meta-training and generally reducing the number of first-order updates required in inference, which could be expensive for large models. Finally, we derive a probabilistic bound that quantifies the performance gap between training on the learned low-dimensional manifold and the full parameterization. We validate our approach on a family of Bouc-Wen oscillators, which is a well-studied nonlinear system identification benchmark. We demonstrate that we are able to learn accurate models even in small-data scenarios.

cs.LG↗

On Two-Player Scalar Discounted Linear Quadratic Games

This paper studies feedback Nash equilibria (FNE) in scalar two-player discounted linear-quadratic games. By explicitly discounting the objective function, we reveal the existence of finite-cost equilibria that do not necessarily stabilize the system, motivating a distinction between stable FNE and FNE. We provide a sufficient condition ensuring that every FNE is stabilizing, together with an analytical characterization of the existence, uniqueness, and multiplicity of FNE. For the symmetric setting, closed-form expressions are derived together with a complete characterization of multiplicity in terms of the game parameters. The local attractive and repelling properties of a FNE under the best-response dynamics are characterized and related to multiplicity in the symmetric setting. Analytical and numerical results further reveal an anti-coordination structure in the value functions when multiple FNE exist. Finally, the Community Cost is investigated, showing how the ordering of FNE depends on the relative weighting of the players' objectives.

math.OC↗

A proximal augmented Lagrangian method for nonconvex optimization with equality and inequality constraints

We propose an inexact proximal augmented Lagrangian method (P-ALM) for nonconvex structured optimization problems. The proposed method features an easily implementable rule not only for updating the penalty parameters, but also for adaptively tuning the proximal term. It allows the penalty parameter to grow rapidly in the early stages to speed up progress, while ameliorating the issue of ill-conditioning in later iterations, a well-known drawback of the traditional approach of linearly increasing the penalty parameters. A key element in our analysis lies in the observation that the augmented Lagrangian can be controlled effectively along the iterates, provided an initial feasible point is available. Our analysis, while simple, provides a new theoretical perspective about P-ALM and, as a by-product, results in similar convergence properties for its non-proximal variant, the classical augmented Lagrangian method (ALM). Numerical experiments, including convex and nonconvex problem instances, demonstrate the effectiveness of our approach.

math.OC↗

Learning generalized Nash equilibria from pairwise preferences

Generalized Nash Equilibrium Problems (GNEPs) arise in many applications, including non-cooperative multi-agent control problems. Although many methods exist for finding generalized Nash equilibria, most of them rely on assuming knowledge of the objective functions or being able to query the best responses of the agents. We present a method for learning solutions of GNEPs only based on querying agents for their preference between two alternative decisions. We use the collected preference data to learn a GNEP whose equilibrium approximates a GNE of the underlying (unknown) problem. Preference queries are selected using an active-learning strategy that balances exploration of the decision space and exploitation of the learned GNEP. We present numerical results on game-theoretic linear quadratic regulation problems, as well as on other literature GNEP examples, showing the effectiveness of the proposed method.

cs.GT↗

Learning Parametric Monotone Games

We study the problem of learning from data a parametric Nash equilibrium (NE) problem that is monotone (or strongly monotone) for all parameter values. In the presence of local and shared convex constraints, monotonicity enables efficient computation of generalized Nash equilibria of the learned game. We consider two learning scenarios: (i) direct learning of the NE problem from samples of the agents' costs, and (ii) inverse learning of surrogate agents' costs from samples of their best responses. We propose two methods to solve these tasks. The first is a penalty-based approach that promotes monotonicity of the learned game during training. The second, based on a representation theorem we introduce for a broad class of monotone games, parameterizes the agents' costs so that monotonicity of the NE problem is guaranteed by construction, for all parameter values, regardless of the training data used. We illustrate the applicability of the proposed methods on several numerical examples. A Python library and the examples reported in the paper are available at https://github.com/bemporad/learn_monotone_games.

math.OC↗

Solving Monotone Linear-Quadratic Generalized Nash Equilibrium Problems via Quadratic Programming

We consider generalized Nash equilibrium problems among $N$ players with convex quadratic costs and shared affine constraints, assuming only that the game's pseudogradient is merely monotone. We show that computing a variational generalized Nash equilibrium (v-GNE) is equivalent to solving a single convex quadratic program (QP) derived from the players' joint Karush--Kuhn--Tucker conditions. Building on this, we show that the regularization of such a QP yields an $\varepsilon$-approximated v-GNE with suboptimality vanishing linearly in the regularization parameter. Next, we propose an accelerated proximal-point scheme and an accelerated projected-gradient method, both attaining an $\mathcal O(1/k^2)$-approximated v-GNE at the $k$-th iteration. We also demonstrate that an invertible Jacobian of the game allows for reduction to a lower-dimensional QP. Theoretical analysis and numerical experiments show the proposed methods substantially outperform the existing approaches to solve monotone linear-quadratic v-GNE problems.

math.OC↗

Solving Multiparametric Generalized Nash Equilibrium Problems and Explicit Game-Theoretic Model Predictive Control

We present a method for computing explicit solutions to parametric generalized Nash equilibrium (GNE) problems with convex quadratic cost functions and linear coupling and local constraints. Assuming that the parameters enter only the linear terms of the cost functions and the constraint right-hand sides, we provide the exact multiparametric solution of the GNE problem. Such a solution enables: (i) minimal real-time computation; (ii) inherent interpretability and explainability, as well as exact enumeration of all multiple equilibria; (iii) selection of desired GNE solution types in the case of infinitely many equilibria; and (iv) zero-shot updates of the GNE solution in response to changes in constraint right-hand sides and/or linear costs. In line with explicit model predictive control (MPC) approaches, we apply our method to solve game-theoretic MPC problems, also known as receding horizon games, explicitly. We compare its performance against centralized solvers in a battery charging game and a toy two-mass-spring-damper system control problem. A Python implementation of the algorithms presented in this paper is available at https://github.com/bemporad/nash_mpqp.

eess.SY↗

Learning practically stabilizing output-feedback nonlinear controllers

This paper addresses the problem of learning an output-feedback surrogate controller offline that approximates a given, possibly computationally expensive, nonlinear controller-observer pair. The surrogate is modeled as a recurrent dynamical system and is trained to imitate closed-loop input/output trajectories generated by the given controller. Beyond imitation accuracy, the offline training problem promotes input-to-state practical stability by incorporating estimated state trajectories to learn a candidate Lyapunov function. The approach is validated on a nonlinear continuous stirred tank reactor, where constraint satisfaction and practical stability are assessed through a probabilistic validation approach. The numerical results highlight the benefit of jointly learning the Lyapunov function by comparing against an imitation-only baseline.

eess.SY↗

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

This paper studies feedback Nash equilibria (FNE) in scalar discounted linear quadratic (LQ) games with $N$ players. By explicitly incorporating the discount factor, we show that finite-cost equilibria may fail to stabilize the original system, motivating a distinction between FNE and stable FNE together with a sufficient stability condition. Based on a parametric characterization of the policies, we propose numerical methods for computing all equilibria. Particular attention is devoted to the symmetric game, where a closed-form expression of the symmetric FNE and conditions for the existence of up to $M\leq2^N-2$ equilibria are derived. Numerical experiments illustrate how equilibrium multiplicity depends on the game configuration and highlight the emergence of finite-cost non-stabilizing equilibria.

eess.SY↗

Amortized Nonlinear Model Predictive Control

Nonlinear Model Predictive Control requires solving a constrained nonlinear program (NLP) in real-time at every sampling instant, a computational bottleneck that limits deployment on resource-constrained hardware or at high sampling rates. We address this challenge for the broad class of input-affine nonlinear systems to show that the optimal control move can be approximated by a state-dependent quadratic program (QP) whose cost parameters depend on the current state and reference. We propose a single-network residual-corrector architecture: a state-dependent analytic baseline provides initial QP parameters, and the network learns only the corrections needed to match the full NLP solution; the QP is solved by a differentiable interior-point layer, guaranteeing constraint satisfaction for the first control action. The network is trained offline on data generated by an NLP solver using a hybrid loss that combines supervised imitation and KKT-residual penalties. We validate the approach on a three-link planar robotic arm with Cartesian end-effector tracking, demonstrating orders-of-magnitude speedup over the NLP solver while maintaining comparable tracking performance.

eess.SY↗

Towards A Goldfarb-Idnani Variant for Strongly Monotone Linear-Quadratic Games

We analyze a simple variant of the Goldfarb-Idnani (GI) dual active-set method for computing variational generalized Nash equilibria of strongly monotone N-player games with convex quadratic costs and shared affine inequality and equality constraints. We show that several properties of the GI algorithm are maintained in spite of having a possibly non-symmetric pseudogradient matrix in the joint KKT system of the game, although convergence to an existing equilibrium is not guaranteed as in the original algorithm. Our numerical results show that the method is potentially competitive with alternative state-of-the-art algorithms, including for computing solutions of game-theoretic linear model predictive control laws.

math.OC↗

Active Learning MPC Objective Functions from Preferences

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-based learning (PbL) approach to learn the MPC objective function from preferences over trajectory pairs. However, the real-world application of PbL is often restricted by the significant cost or limited availability of human preference queries. To address this, Active Learning (AL) strategies seek to improve sampling efficiency, reducing the labeling effort required to obtain a well-performing classifier. We present two AL strategies for learning the MPC objective function from human preferences over pairwise system trajectories: a pool-based strategy that selects trajectory pairs that are both uncertain under the current surrogate and diverse relative to previously labeled comparisons, and a query-synthesis strategy that incorporates new trajectories using the current surrogate-driven MPC. Numerical results show that the proposed strategies yield closed-loop behaviors that align more with the expressed preference using fewer number of queries compared to a random sampling approach.

eess.SY↗

Worst-case Nonlinear Regression with Error Bounds

We propose an active-learning method for nonlinear minimax regression. Given a nonlinear function that can be arbitrarily evaluated over a compact set, we fit a surrogate model, such as a feedforward neural network, by minimizing the maximum absolute approximation error. To handle the nonsmoothness of this worst-case loss, we introduce a smooth $L_\infty$ approximation that enables efficient gradient-based training. The training set is iteratively enriched by querying points of largest error via global optimization. We also derive constant and input-dependent worst-case error bounds over the entire input domain. The approach is validated on approximations of nonlinear functions and nonconvex sets, uncertain models of nonlinear dynamics, and explicit model predictive control laws. A Python library is available at https://github.com/bemporad/maxfit.

eess.SY↗

Rollout Then Optimize: A One-Step Newton Refinement of Learned Policies for Nonlinear Model Predictive Control

We propose a computationally efficient rollout-then-optimize method to improve a learned control policy at deployment time. A learned policy provides a nominal trajectory, which is refined online by a single Newton step implemented via a Riccati recursion within a model predictive control (MPC) scheme. This refinement combines model knowledge with the learned policy at minimal additional computational cost. We establish bounds on the approximation error of the learned policy relative to the MPC policy and show that one Newton step reduces the suboptimality of the learned rollout quadratically in the policy approximation error. The proposed controller is validated in simulation on a constrained trajectory-tracking task for a quadcopter with nonlinear dynamics. Results highlight that the Newton step significantly improves the learned policy, achieving performance close to a fully converged MPC solution while requiring roughly half of the computational time. The code is available at https://github.com/aghezz1/rl-riccati.

math.OC↗

Parametric Nonconvex Optimization via Convex Surrogates

This paper presents a novel learning-based approach to construct a surrogate problem that approximates a given parametric nonconvex optimization problem. The surrogate function is designed to be the minimum of a finite set of functions, given by the composition of convex and monotonic terms, so that the surrogate problem can be solved directly through parallel convex optimization. As a proof of concept, numerical experiments on a nonconvex path tracking problem confirm the approximation quality of the proposed method.

math.OC↗