arXiv subjects

Konstantinos G. Papakonstantinou

Publications and source records attributed to Konstantinos G. Papakonstantinou.

14 recordsLinked to original sources

arXiv2026

Graph-Based Inference and Topology-Aware Multi-Agent Reinforcement Learning for Large-Scale Railway Network Management

Modern infrastructure asset management constitutes a complex sequential decision-making problem, characterized by long planning horizons and system-level interactions, such as spatial deterioration correlations and economies of scale. While deep reinforcement learning has shown promise in optimizing maintenance policies, scaling to real-world networks remains challenging. Centralized approaches become computationally intractable in large-scale systems, whereas decentralized approaches often fail to capture essential coordination mechanisms. To address these challenges, we propose a graph-based framework that integrates accurate environment modeling with scalable decision support. First, we employ a hierarchical Bayesian model leveraging a Gaussian Process on Graph kernel to infer a realistic, spatially correlated networked environment of railway maintenance planning from real-world data provided by the Swiss Federal Railways. Second, we introduce a topology-aware Multi-Agent Reinforcement Learning (MARL) framework by integrating graph neural networks and graph Transformers to optimize network-level policies. A central contribution of this work is the demonstration of scalability through zero-shot transfer learning: graph-based agents, trained only on small network portions, are successfully deployed in a zero-shot manner on large-scale unseen networks without any retraining. Numerical results indicate that the proposed method significantly outperforms optimized heuristics and standard MARL baselines, reducing computational training time while maintaining superior performance on large-scale networks.

cs.LG↗

arXiv2026

Probabilistic Hazard Analysis Framework with Stochastic Optimal Control for Deteriorating Civil Infrastructure Systems

The safety and resilience of civil infrastructure systems are increasingly threatened by compounded risks from various hazard events and structural deterioration due to environmental stressors. This study presents a comprehensive risk-informed, life-cycle optimization framework that extends the Performance-Based Earthquake Engineering (PBEE) and probabilistic seismic loss estimation paradigms by combining hazard uncertainties, nonstationary deterioration, structural damage accumulation, and state-dependent fragility assessments, with optimal, adaptive maintenance strategies in time. The life-cycle cost optimization is formulated in this work as a Markov Decision Process (MDP) problem, utilizing derived, transition matrices reflecting time-variant deterioration effects and hazard risks. To mitigate the curse of dimensionality in system-level optimization, a novel tensor-based method exploiting Kronecker-factored transition dynamics is introduced, reducing complexity from exponential to linear in the number of components while still preserving exact, global dynamic programming solutions. Overall, the framework is general and versatile, able to accommodate various hazard types. A seismic hazard application is, however, demonstrated and explained in detail in this work. The developed methodology eventually provides decision-makers with a practical, data-driven tool toward cost effective risk mitigation of civil infrastructure systems.

eess.SY↗

arXiv2026

Quadratic Point Estimate Method for Uncertainty Quantification with Dependent Non-Gaussian Inputs

As an extension of the Point Estimate Method (PEM) to evaluate probabilistic moments of quantities of interest (QoI) in general $n$-dimensional spaces, the Quadratic Point Estimate Method (QPEM) has been recently developed. This new method is defined to fully represent up to fifth-order input moments in the Gaussian space, providing general analytical expressions for sample locations and weights, without requiring any numerical optimization. The QPEM can significantly improve the estimation accuracy of the output QoI moments, in relation to PEM-based methods whose numbers of sigma points grow linearly with the problem dimension, while at the same time having an affordable and competitive computational cost up to a considerable number of dimensions. The QPEM is further enhanced in this work by enabling copula integration into the framework, which enables effective modeling of the joint input probability density function by estimating marginals and the dependence structure of the involved random variables. The validity and efficient performance of the copula-based QPEM are showcased against numerous other sampling methods in various examples considering two practical scenarios: (i) when the joint dependence structure can be inferred from data, and (ii) when only marginal distributions and correlation matrices are known.

math.NA↗

arXiv2026

The price of decentralization in managing engineering systems through multi-agent reinforcement learning

Inspection and maintenance (I&M) planning involves sequential decision making under uncertainties and incomplete information, and can be modeled as a partially observable Markov decision process (POMDP). While single-agent deep reinforcement learning provides approximate solutions to POMDPs, it does not scale well in multi-component systems. Scalability can be achieved through multi-agent deep reinforcement learning (MADRL), which decentralizes decision-making across multiple agents, locally controlling individual components. However, this decentralization can induce cooperation pathologies that degrade the optimality of the learned policies. To examine these effects in I&M planning, we introduce a set of deteriorating systems in which redundancy is varied systematically. These benchmark environments are designed such that computation of centralized (near-)optimal policies remains tractable, enabling direct comparison of solution methods. We implement and benchmark a broad set of MADRL algorithms spanning fully centralized and decentralized training paradigms, from value-factorization to actor-critic methods. Our results show a clear effect of redundancy on coordination: MADRL algorithms achieve near-optimal performance in series-like settings, whereas increasing redundancy amplifies coordination challenges and can lead to optimality losses. Nonetheless, decentralized agents learn structured policies that consistently outperform optimized heuristic baselines, highlighting both the promise and current limitations of decentralized learning for scalable maintenance planning.

cs.MA↗

arXiv2025

Deep Belief Markov Models for POMDP Inference

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The POMDP framework allows for modeling and solving sequential decision-making problems under observation uncertainty. In complex, high-dimensional, partially observable environments, existing methods for inference based on exact computations (e.g., via Bayes' theorem) or sampling algorithms do not scale well. Furthermore, ground truth states may not be available for learning the exact transition dynamics. DBMMs extend deep Markov models into the partially observable decision-making framework and allow efficient belief inference entirely based on available observation data via variational inference methods. By leveraging the potency of neural networks, DBMMs can infer and simulate non-linear relationships in the system dynamics and naturally scale to problems with high dimensionality and discrete or continuous variables. In addition, neural network parameters can be dynamically updated efficiently based on data availability. DBMMs can thus be used to infer a belief variable, thus enabling the derivation of POMDP solutions over the belief space. We evaluate the efficacy of the proposed methodology by evaluating the capability of model-formulation agnostic inference of DBMMs in benchmark problems that include discrete and continuous variables.

cs.LG↗

arXiv2025

Gradient-free Importance Sampling Scheme for Efficient Reliability Estimation

This work presents a novel gradient-free importance sampling-based framework for precisely and efficiently estimating rare event probabilities, often encountered in reliability analyses of engineering systems. The approach is formulated around our foundational Approximate Sampling Target with Post-processing Adjustment (ASTPA) methodology. ASTPA uniquely constructs and directly samples an unnormalized target distribution, relaxing the optimal importance sampling distribution (ISD). The target's normalizing constant is then estimated using our inverse importance sampling (IIS) scheme, employing an ISD fitted based on the obtained samples. In this work, a gradient-free sampling method within ASTPA is developed through a guided dimension-robust preconditioned Crank-Nicolson (pCN) algorithm, particularly suitable for black-box computational models where analytical gradient information is not available. To boost the sampling efficiency of pCN in our context, a computationally effective, general discovery stage for the rare event domain is devised, providing (multi-modal) rare event samples used in initializing the pCN chains. A series of diverse test functions and engineering problems involving high dimensionality and strong nonlinearity is presented, demonstrating the advantages of the proposed framework compared to several state-of-the-art sampling methods.

stat.ME↗

arXiv2025

A Direct Importance Sampling-based Framework for Rare Event Uncertainty Quantification in Non-Gaussian Spaces

This work introduces a novel framework for precisely and efficiently estimating rare event probabilities in complex, high-dimensional non-Gaussian spaces, building on our foundational Approximate Sampling Target with Post-processing Adjustment (ASTPA) approach. An unnormalized sampling target is first constructed and sampled, relaxing the optimal importance sampling distribution and appropriately designed for non-Gaussian spaces. Post-sampling, its normalizing constant is estimated using a stable inverse importance sampling procedure, employing an importance sampling density based on the already available samples. The sought probability is then computed based on the estimates evaluated in these two stages. The proposed estimator is theoretically analyzed, proving its unbiasedness and deriving its analytical coefficient of variation. To sample the constructed target, we resort to our developed Quasi-Newton mass preconditioned Hamiltonian MCMC (QNp-HMCMC) and we prove that it converges to the correct stationary target distribution. To avoid the challenging task of tuning the trajectory length in complex spaces, QNp-HMCMC is effectively utilized in this work with a single-step integration. We thus show the equivalence of QNp-HMCMC with single-step implementation to a unique and efficient preconditioned Metropolis-adjusted Langevin algorithm (MALA). An optimization approach is also leveraged to initiate QNp-HMCMC effectively, and the implementation of the developed framework in bounded spaces is eventually discussed. A series of diverse problems involving high dimensionality (several hundred inputs), strong nonlinearity, and non-Gaussianity is presented, showcasing the capabilities and efficiency of the suggested framework and demonstrating its advantages compared to relevant state-of-the-art sampling methods.

stat.ME↗

arXiv2024

Quadratic Point Estimate Method for Probabilistic Moments Computation

This paper presents in detail the originally developed Quadratic Point Estimate Method (QPEM), aimed at efficiently and accurately computing the first four output moments of probabilistic distributions, using 2n^2+1 sample (or sigma) points, with n, the number of input random variables. The proposed QPEM particularly offers an effective, superior, and practical alternative to existing sampling and quadrature methods for low- and moderately-high-dimensional problems. Detailed theoretical derivations are provided proving that the proposed method can achieve a fifth or higher-order accuracy for symmetric input distributions. Various numerical examples, from simple polynomial functions to nonlinear finite element analyses with random field representations, support the theoretical findings and further showcase the validity, efficiency, and applicability of the QPEM, from low- to high-dimensional problems.

math.NA↗

arXiv2024

Monitoring-Supported Value Generation for Managing Structures and Infrastructure Systems

To maximize its value, the design, development and implementation of Structural Health Monitoring (SHM) should focus on its role in facilitating decision support. In this position paper, we offer perspectives on the synergy between SHM and decision-making. We propose a classification of SHM use cases aligning with various dimensions that are closely linked to the respective decision contexts. The types of decisions that have to be supported by the SHM system within these settings are discussed along with the corresponding challenges. We provide an overview of different classes of models that are required for integrating SHM in the decision-making process to support management and operation and maintenance of structures and infrastructure systems. Fundamental decision-theoretic principles and state-of-the-art methods for optimizing maintenance and operational decision-making under uncertainty are briefly discussed. Finally, we offer a viewpoint on the appropriate course of action for quantifying, validating and maximizing the added value generated by SHM. This work aspires to synthesize the different perspectives of the SHM, Prognostic Health Management (PHM), and reliability communities, and deliver a roadmap towards monitoring-based decision support.

cs.CY↗

arXiv2023

POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenance

Partially Observable Markov Decision Processes (POMDPs) can model complex sequential decision-making problems under stochastic and uncertain environments. A main reason hindering their broad adoption in real-world applications is the lack of availability of a suitable POMDP model or a simulator thereof. Available solution algorithms, such as Reinforcement Learning (RL), require the knowledge of the transition dynamics and the observation generating process, which are often unknown and non-trivial to infer. In this work, we propose a combined framework for inference and robust solution of POMDPs via deep RL. First, all transition and observation model parameters are jointly inferred via Markov Chain Monte Carlo sampling of a hidden Markov model, which is conditioned on actions, in order to recover full posterior distributions from the available data. The POMDP with uncertain parameters is then solved via deep RL techniques with the parameter distributions incorporated into the solution via domain randomization, in order to develop solutions that are robust to model uncertainty. As a further contribution, we compare the use of transformers and long short-term memory networks, which constitute model-free RL solutions, with a model-based/model-free hybrid approach. We apply these methods to the real-world problem of optimal maintenance planning for railway assets.

cs.LG↗

arXiv2023

Hamiltonian MCMC methods for estimating rare events probabilities in high-dimensional problems

Accurate and efficient estimation of rare events probabilities is of significant importance, since often the occurrences of such events have widespread impacts. The focus in this work is on precisely quantifying these probabilities, often encountered in reliability analysis of complex engineering systems, based on an introduced framework termed Approximate Sampling Target with Post-processing Adjustment (ASTPA), which herein is integrated with and supported by gradient-based Hamiltonian Markov Chain Monte Carlo (HMCMC) methods. The developed techniques in this paper are applicable from low- to high-dimensional stochastic spaces, and the basic idea is to construct a relevant target distribution by weighting the original random variable space through a one-dimensional output likelihood model, using the limit-state function. To sample from this target distribution, we exploit HMCMC algorithms, a family of MCMC methods that adopts physical system dynamics, rather than solely using a proposal probability distribution, to generate distant sequential samples, and we develop a new Quasi-Newton mass preconditioned HMCMC scheme (QNp-HMCMC), which is particularly efficient and suitable for high-dimensional spaces. To eventually compute the rare event probability, an original post-sampling step is devised using an inverse importance sampling procedure based on the already obtained samples. The statistical properties of the estimator are analyzed as well, and the performance of the proposed methodology is examined in detail and compared against Subset Simulation in a series of challenging low- and high-dimensional problems.

stat.ME↗

arXiv2022

Bridging POMDPs and Bayesian decision making for robust maintenance planning under model uncertainty: An application to railway systems

Structural Health Monitoring (SHM) describes a process for inferring quantifiable metrics of structural condition, which can serve as input to support decisions on the operation and maintenance of infrastructure assets. Given the long lifespan of critical structures, this problem can be cast as a sequential decision making problem over prescribed horizons. Partially Observable Markov Decision Processes (POMDPs) offer a formal framework to solve the underlying optimal planning task. However, two issues can undermine the POMDP solutions. Firstly, the need for a model that can adequately describe the evolution of the structural condition under deterioration or corrective actions and, secondly, the non-trivial task of recovery of the observation process parameters from available monitoring data. Despite these potential challenges, the adopted POMDP models do not typically account for uncertainty on model parameters, leading to solutions which can be unrealistically confident. In this work, we address both key issues. We present a framework to estimate POMDP transition and observation model parameters directly from available data, via Markov Chain Monte Carlo (MCMC) sampling of a Hidden Markov Model (HMM) conditioned on actions. The MCMC inference estimates distributions of the involved model parameters. We then form and solve the POMDP problem by exploiting the inferred distributions, to derive solutions that are robust to model uncertainty. We successfully apply our approach on maintenance planning for railway track assets on the basis of a "fractal value" indicator, which is computed from actual railway monitoring data.

cs.AI↗

arXiv2022

Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning

In the context of modern environmental and societal concerns, there is an increasing demand for methods able to identify management strategies for civil engineering systems, minimizing structural failure risks while optimally planning inspection and maintenance (I&M) processes. Most available methods simplify the I&M decision problem to the component level due to the computational complexity associated with global optimization methodologies under joint system-level state descriptions. In this paper, we propose an efficient algorithmic framework for inference and decision-making under uncertainty for engineering systems exposed to deteriorating environments, providing optimal management strategies directly at the system level. In our approach, the decision problem is formulated as a factored partially observable Markov decision process, whose dynamics are encoded in Bayesian network conditional structures. The methodology can handle environments under equal or general, unequal deterioration correlations among components, through Gaussian hierarchical structures and dynamic Bayesian networks. In terms of policy optimization, we adopt a deep decentralized multi-agent actor-critic (DDMAC) reinforcement learning approach, in which the policies are approximated by actor neural networks guided by a critic network. By including deterioration dependence in the simulated environment, and by formulating the cost model at the system level, DDMAC policies intrinsically consider the underlying system-effects. This is demonstrated through numerical experiments conducted for both a 9-out-of-10 system and a steel frame under fatigue deterioration. Results demonstrate that DDMAC policies offer substantial benefits when compared to state-of-the-art heuristic approaches. The inherent consideration of system-effects by DDMAC strategies is also interpreted based on the learned policies.

cs.AI↗

arXiv2019

A direct Hamiltonian MCMC approach for reliability estimation

Accurate and efficient estimation of rare events probabilities is of significant importance, since often the occurrences of such events have widespread impacts. The focus in this work is on precisely quantifying these probabilities, often encountered in reliability analysis of complex engineering systems, by introducing a gradient-based Hamiltonian Markov Chain Monte Carlo (HMCMC) framework, termed Approximate Sampling Target with Post-processing Adjustment (ASTPA). The basic idea is to construct a relevant target distribution by weighting the high-dimensional random variable space through a one-dimensional likelihood model, using the limit-state function. To sample from this target distribution we utilize HMCMC algorithms that produce Markov chain samples based on Hamiltonian dynamics rather than random walks. We compare the performance of typical HMCMC scheme with our newly developed Quasi-Newton based mass preconditioned HMCMC algorithm that can sample very adeptly, particularly in difficult cases with high-dimensionality and very small failure probabilities. To eventually compute the probability of interest, an original post-sampling step is devised at this stage, using an inverse importance sampling procedure based on the samples. The involved user-defined parameters of ASTPA are then discussed and general default values are suggested. Finally, the performance of the proposed methodology is examined in detail and compared against Subset Simulation in a series of static and dynamic low- and high-dimensional benchmark problems.

stat.CO↗