English
Related papers

Related papers: Equilibrium Propagation for Learning in Lagrangian…

200 papers

Primal-dual gradient dynamics that find saddle points of a Lagrangian have been widely employed for handling constrained optimization problems. Building on existing methods, we extend the augmented primal-dual gradient dynamics (Aug-PDGD)…

Optimization and Control · Mathematics 2020-11-19 Yujie Tang , Guannan Qu , Na Li

Traditional control theory-based methods require tailored engineering for each system and constant fine-tuning. In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the…

Systems and Control · Electrical Eng. & Systems 2024-09-21 Yixuan Sun , Sami Khairy , Richard B. Vilim , Rui Hu , Akshay J. Dave

Deep learning models are able to approximate one specific dynamical system but struggle at learning generalisable dynamics, where dynamical systems obey the same laws of physics but contain different numbers of elements (e.g., double- and…

Machine Learning · Computer Science 2022-07-05 Yupu Lu , Shijie Lin , Guanqi Chen , Jia Pan

We provide quantitative estimates in total variation distance for positive semi-groups, which can be non-conservative and non-homogeneous. The techniques relies on a family of conservative semigroups that describes a typical particle and…

Analysis of PDEs · Mathematics 2020-07-22 Vincent Bansaye , Bertrand Cloez , Pierre Gabriel

High performance tracking control can only be achieved if a good model of the dynamics is available. However, such a model is often difficult to obtain from first order physics only. In this paper, we develop a data-driven control law that…

Systems and Control · Computer Science 2018-11-20 Thomas Beckers , Jonas Umlauft , Dana Kulić , Sandra Hirche

One key in real-life Nash equilibrium applications is to calibrate players' cost functions. To leverage the approximation ability of neural networks, we proposed a general framework for optimizing and learning Nash equilibrium using neural…

Computer Science and Game Theory · Computer Science 2024-09-04 Di Zhang , Wei Gu , Qing Jin

Learning and predicting the dynamics of physical systems requires a profound understanding of the underlying physical laws. Recent works on learning physical laws involve generalizing the equation discovery frameworks to the discovery of…

Machine Learning · Statistics 2023-10-11 Tapas Tripura , Souvik Chakraborty

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size $\gamma$ and momentum parameter…

Machine Learning · Computer Science 2024-03-11 Hristo Papazov , Scott Pesme , Nicolas Flammarion

Real-world physics can only be analytically modeled with a certain level of precision for modern intricate robotic systems. As a result, tracking aggressive trajectories accurately could be challenging due to the existence of residual…

Robotics · Computer Science 2026-04-16 Kexin Guo , Zihan Yang , Yuhang Liu , Jindou Jia , Xiang Yu

We use a reinforcement learning approach to reduce entropy production in a closed quantum system brought out of equilibrium. Our strategy makes use of an external control Hamiltonian and a policy gradient technique. Our approach bears no…

Quantum Physics · Physics 2024-02-21 Sofia Sgroi , G. Massimo Palma , Mauro Paternostro

Adversarial training has emerged as an effective approach to train robust neural network models that are resistant to adversarial attacks, even in low-label regimes where labeled data is scarce. In this paper, we introduce a novel…

Machine Learning · Computer Science 2024-11-28 Tian Ye , Rajgopal Kannan , Viktor Prasanna

Employing a phase space which includes the (Riemann-Liouville) fractional derivative of curves evolving on real space, we develop a restricted variational principle for Lagrangian systems yielding the so-called restricted fractional…

Mathematical Physics · Physics 2018-03-01 Fernando Jiménez , Sina Ober-Blöbaum

In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known.…

Machine Learning · Statistics 2020-03-05 Kei Ota , Devesh K. Jha , Tomoaki Oiki , Mamoru Miura , Takashi Nammoto , Daniel Nikovski , Toshisada Mariyama

This paper explores transverse coordinates for the purpose of orbitally stabilizing periodic motions of nonlinear, control-affine dynamical systems. It is shown that the dynamics of any (minimal or excessive) set of transverse coordinates,…

Systems and Control · Electrical Eng. & Systems 2020-05-12 Christian Fredrik Sætre , Anton Shiriaev

Traditional backpropagation of error, though a highly successful algorithm for learning in artificial neural network models, includes features which are biologically implausible for learning in real neural circuits. An alternative called…

Machine Learning · Computer Science 2020-11-06 Nasir Ahmad , Marcel A. J. van Gerven , Luca Ambrogioni

We discuss some Lagrangian and presymplectic models concerning test particles in electromagnetic and gravitational fields, with the aim of describing an upper bound to the acceleration. Some models are based on the relativistic phase space…

High Energy Physics - Theory · Physics 2007-05-23 M. Toller

Learning to control unknown nonlinear dynamical systems is a fundamental problem in reinforcement learning and control theory. A commonly applied approach is to first explore the environment (exploration), learn an accurate model of it…

Machine Learning · Computer Science 2023-06-16 Andrew Wagenmaker , Guanya Shi , Kevin Jamieson

Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws. Unfortunately common deep learning approaches to control, such as deep reinforcement learning, require an unrealistic amount…

Robotics · Computer Science 2019-08-06 Michael Lutter , Kim Listmann , Jan Peters

We develop here the method for obtaining approximate stability boundaries in the space of parameters for systems with parametric excitation. The monodromy (Floquet) matrix of linearized system is found by averaging method. For system with 2…

Dynamical Systems · Mathematics 2019-12-24 Anton O. Belyakov , Alexander P. Seyranian

The unique fluctuation-dissipation theorem for equilibrium stands in contrast with the wide variety of nonequilibrium linear response formulae. Their most traditional approach is "analytic", which, in the absence of detailed balance,…

Statistical Mechanics · Physics 2013-01-21 Marco Baiesi , Christian Maes