English
Related papers

Related papers: Policy Optimization for PDE Control with a Warm St…

200 papers

Plateaus, where an agent's performance stagnates at a suboptimal level, are a common problem in deep on-policy RL. Focusing on PPO due to its widespread adoption, we show that plateaus in certain regimes arise not because of known…

Machine Learning · Computer Science 2026-03-09 Michael Beukman , Khimya Khetarpal , Zeyu Zheng , Will Dabney , Jakob Foerster , Michael Dennis , Clare Lyle

We investigate an optimization problem governed by an elliptic partial differential equation with uncertain parameters. We introduce a robust optimization framework that accounts for uncertain model parameters. The resulting non-linear…

Optimization and Control · Mathematics 2019-09-24 Alessandro Alla , Michael Hinze , Philip Kolvenbach , Oliver Lass , Stefan Ulbrich

Traditional approaches to stabilizing hyperbolic PDEs, such as PDE backstepping, often encounter challenges when dealing with high-dimensional or complex nonlinear problems. Their solutions require high computational and analytical costs.…

Analysis of PDEs · Mathematics 2024-11-08 Xianhe Zhang , Yu Xiao , Xiaodong Xu , Biao Luo

Ordinary Differential Equations are a simple but powerful framework for modeling complex systems. Parameter estimation from times series can be done by Nonlinear Least Squares (or other classical approaches), but this can give…

Methodology · Statistics 2014-10-29 Quentin Clairon , Nicolas Brunel

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

Control of nonlinear distributed parameter systems (DPS) under uncertainty is a meaningful task for many industrial processes. However, both intrinsic uncertainty and high dimensionality of DPS require intensive computations, while…

Optimization and Control · Mathematics 2024-10-17 Min Tao , Ioannis Zacharopoulos , Constantinos Theodoropoulos

We introduce an alternative approach for the analysis and numerical approximation of the optimal feedback control mapping. It consists in looking at a typical optimal control problem in such a way that feasible controls are mappings…

Optimization and Control · Mathematics 2017-06-09 Pablo Pedregal

In this paper, we analyze the convergence of several discretize-then-optimize algorithms, based on either a second-order or a fourth-order finite difference discretization, for solving elliptic PDE-constrained optimization or optimal…

Numerical Analysis · Mathematics 2018-08-14 Jun Liu , Zhu Wang

In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with…

Machine Learning · Computer Science 2020-03-23 Yunhao Tang , Shipra Agrawal

Physics-based models often involve large systems of parametrized partial differential equations, where design parameters control various properties. However, high-fidelity simulations of such systems on large domains or with high grid…

Computational Physics · Physics 2025-05-15 Diba Behnoudfar

Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse.…

Machine Learning · Computer Science 2018-11-01 Alberto Maria Metelli , Matteo Papini , Francesco Faccio , Marcello Restelli

Mode-dependent architectural components (layers that behave differently during training and evaluation, such as Batch Normalization or dropout) are commonly used in visual reinforcement learning but can destabilize on-policy optimization.…

Machine Learning · Computer Science 2026-02-06 Mohamad Mohamad , Francesco Ponzio , Xavier Descombes

Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a…

Machine Learning · Computer Science 2020-06-22 Ahmed Touati , Amy Zhang , Joelle Pineau , Pascal Vincent

This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control…

Systems and Control · Electrical Eng. & Systems 2021-03-23 Hossein Nejatbakhsh Esfahani , Arash Bahari Kordabad , Sebastien Gros

We present a new data-driven reduced-order modeling approach to efficiently solve parametrized partial differential equations (PDEs) for many-query problems. This work is inspired by the concept of implicit neural representation (INR),…

Numerical Analysis · Mathematics 2023-11-30 Tianshu Wen , Kookjin Lee , Youngsoo Choi

Residential demand response programs aim to activate demand flexibility at the household level. In recent years, reinforcement learning (RL) has gained significant attention for these type of applications. A major challenge of RL algorithms…

Systems and Control · Electrical Eng. & Systems 2024-03-13 Thijs Peirelinck , Chris Hermans , Fred Spiessens , Geert Deconinck

This work formulates a new approach to reduced modeling of parameterized, time-dependent partial differential equations (PDEs). The method employs Operator Inference, a scientific machine learning framework combining data-driven learning…

Computational Engineering, Finance, and Science · Computer Science 2025-06-16 Shane A McQuarrie , Parisa Khodabakhshi , Karen E Willcox

Reduced-order modeling (ROM) commonly refers to the construction, based on a few solutions (referred to as snapshots) of an expensive discretized partial differential equation (PDE), and the subsequent application of low-dimensional…

Numerical Analysis · Mathematics 2019-05-22 Martin Hess , Alessandro Alla , Annalisa Quaini , Gianluigi Rozza , Max Gunzburger

Direct Preference Optimization (DPO) has been widely adopted for large language model alignment due to its simple training procedure and lack of an explicit reward model. However, in iterative DPO, when the policy model from the previous…

Information Retrieval · Computer Science 2026-05-25 Lingling Fu , Yongfu Xu

Continuous monitoring and real-time control of high-dimensional distributed systems are often crucial in applications to ensure a desired physical behavior, without degrading stability and system performances. Traditional feedback control…

Optimization and Control · Mathematics 2024-12-16 Matteo Tomasetto , Francesco Braghin , Andrea Manzoni
‹ Prev 1 3 4 5 6 7 10 Next ›