paper-with-me

홈 › Papers

DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control

2020-09-09 · Victor M. Martinez Alvarez, Rareş Roşca, Cristian G. Fălcuţescu

We present a novel approach (DyNODE) that captures the underlying dynamics of a system by incorporating control in a neural ordinary differential equation framework. We conduct a systematic evaluation and comparison of our method and standard neural network architectures for dynamics modeling. Our results indicate that a simple DyNODE architecture when combined with an actor-critic reinforcement learning (RL) algorithm that uses model predictions to improve the critic's target values, outperforms canonical neural networks, both in sample efficiency and predictive performance across a diverse range of continuous tasks that are frequently used to benchmark RL algorithms. This approach provides a new avenue for the development of models that are more suited to learn the evolution of dynamical systems, particularly useful in the context of model-based reinforcement learning. To assist related work, we have made code available at https://github.com/vmartinezalvarez/DyNODE .

📄 PDF Abstract BibTeX arXiv:2009.04278

Code (1)

vmartinezalvarez/DyNODE 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlModel-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Modelling Latent Dynamics of StyleGAN using Neural ODEs

2022-08-23 · Weihao Xia, Yujiu Yang, Jing-Hao Xue

In this paper, we propose to model the video dynamics by learning the trajectory of independently inverted latent codes from GANs. The entire sequence is seen as discrete-time observations of a continuous trajectory of t…

Video Editing

Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics

2023-12-18 · Lanlan Chen, Kai Wu, Jian Lou, Jing Liu

Modeling continuous-time dynamics constitutes a foundational challenge, and uncovering inter-component correlations within complex systems holds promise for enhancing the efficacy of dynamic modeling. The prevailing appr…

Input-to-State Stable Neural Ordinary Differential Equations with Applications to Transient Modeling of Circuits

2022-02-14 · Alan Yang, Jie Xiong, Maxim Raginsky, Elyse Rosenbaum

This paper proposes a class of neural ordinary differential equations parametrized by provably input-to-state stable continuous-time recurrent neural networks. The model dynamics are defined by construction to be input-t…

Graph Neural Ordinary Differential Equations for Coarse-Grained Socioeconomic Dynamics

2024-07-25 · James Koch, Pranab Roy Chowdhury, Heng Wan, Parin Bhaduri 외

We present a data-driven machine-learning approach for modeling space-time socioeconomic dynamics. Through coarse-graining fine-scale observations, our modeling framework simplifies these complex systems to a set of trac…

Sensitivity

Parameter-varying neural ordinary differential equations with partition-of-unity networks

2022-10-01 · Kookjin Lee, Nathaniel Trask

In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architectur…

Mixture-of-ExpertsUnity