arXiv subjects

Felix Thömmes

Publications and source records attributed to Felix Thömmes.

5 recordsLinked to original sources

arXiv2026

Infinite-Horizon Inverse Linear-Quadratic Differential Games with State- and Control-Dependent Noise

This paper presents a method to solve the inverse problem for N-player infinite-horizon linear-quadratic (LQ) differential games with state- and control-dependent noise. For this stochastic setting, we derive necessary and sufficient conditions for linear feedback Nash equilibria, which take the form of coupled stochastic algebraic Riccati equations. We then derive a kernel representation of these equations to explicitly characterize the set of all cost function parameter combinations across players that are consistent with observed equilibrium trajectories, thereby solving the associated inverse problem. Numerical results illustrate the approach and confirm the theoretical findings, highlighting the inherent ambiguity of the inverse problem.

eess.SY↗

arXiv2026

Policy Iteration for Linear-Quadratic Stochastic Differential Games with State- and Control-Dependent Noise

This paper presents a novel sequential policy iteration (PI) method for stochastic differential games with state- and control-dependent noise. The updates preserve mean-square stability, so that the iteration is well posed. We further derive a closed-form expression for the Fréchet derivative of the sequential PI map at a Nash equilibrium. The resulting characterization reveals how control-dependent noise, policy-evaluation sensitivity, and update ordering govern local error propagation, and yields explicit sufficient conditions for local linear convergence. Since finding an initial stabilizing solution is a major challenge in policy iteration, we also propose a homotopy-based initialization that ensures a valid starting point. The effectiveness of the proposed PI algorithm and the analytical results are verified through a numerical example.

eess.SY↗

arXiv2026

Data-Driven Continuous-Time Linear Quadratic Regulator via Closed-Loop and Reinforcement Learning Parameterizations

This paper studies data-driven approaches to the continuous-time linear quadratic regulator (LQR) problem based on two existing parameterizations, namely a closed-loop (CL) parameterization from behavioral system theory and an integral reinforcement learning (IRL) parameterization. The CL parameterization characterizes the closed-loop system via a matrix that satisfies equality constraints. While this parameterization has been extensively studied for discrete-time systems, we adapt key results to the continuous-time setting and develop a policy iteration (PI) scheme, derive a data-driven continuous-time algebraic Riccati equation (CARE), and introduce an alternative convex problem formulation. The IRL parameterization utilizes off-policy data to perform policy evaluation, which is then used for PI or value iteration. Within the IRL framework, we derive a policy gradient flow and propose convex reformulations of the LQR problem. Finally, we provide a unified treatment of these parameterizations that enables a systematic understanding of existing approaches and clarifies their structural relationships.

math.OC↗

arXiv2026

Inverse Linear-Quadratic Gaussian Differential Games

This paper presents a method for solving the Inverse Stochastic Differential Game (ISDG) problem in finite-horizon linear-quadratic Gaussian (LQG) differential games. The objective is to recover cost function parameters of all players, as well as noise scaling parameters of the stochastic system, consistent with observed trajectories. The proposed framework combines (i) estimation of the feedback strategies, (ii) identification of the cost function parameters via a novel reformulation of the coupled Riccati differential equations, and (iii) maximum likelihood estimation of the noise scaling parameters. Simulation results demonstrate that the approach recovers parameters, yielding trajectories that closely match the observed trajectories.

eess.SY↗

arXiv2024

Automatic Generation of Fast and Accurate Performance Models for Deep Neural Network Accelerators

Implementing Deep Neural Networks (DNNs) on resource-constrained edge devices is a challenging task that requires tailored hardware accelerator architectures and a clear understanding of their performance characteristics when executing the intended AI workload. To facilitate this, we present an automated generation approach for fast performance models to accurately estimate the latency of a DNN mapped onto systematically modeled and concisely described accelerator architectures. Using our accelerator architecture description method, we modeled representative DNN accelerators such as Gemmini, UltraTrail, Plasticine-derived, and a parameterizable systolic array. Together with DNN mappings for those modeled architectures, we perform a combined DNN/hardware dependency graph analysis, which enables us, in the best case, to evaluate only 154 loop kernel iterations to estimate the performance for 4.19 billion instructions achieving a significant speedup. We outperform regression and analytical models in terms of mean absolute percentage error (MAPE) compared to simulation results, while being several magnitudes faster than an RTL simulation.

cs.PF↗