English
Related papers

Related papers: GEM: Group Enhanced Model for Learning Dynamical C…

200 papers

Moving in dynamic pedestrian environments is one of the important requirements for autonomous mobile robots. We present a model-based reinforcement learning approach for robots to navigate through crowded environments. The navigation policy…

Robotics · Computer Science 2020-11-10 Yuxiang Cui , Haodong Zhang , Yue Wang , Rong Xiong

The Finite Element Method (FEM) is a powerful modeling tool for predicting the behavior of soft robots. However, its use for control can be difficult for non-specialists of numerical computation: it requires an optimization of the…

Robotics · Computer Science 2023-07-24 Etienne Ménager , Tanguy Navez , Olivier Goury , Christian Duriez

We present our Generative Enhanced Model (GEM) that we used to create samples awarded the first prize on the FEVER 2.0 Breakers Task. GEM is the extended language model developed upon GPT-2 architecture. The addition of novel target…

Computation and Language · Computer Science 2019-10-02 Piotr Niewinski , Maria Pszona , Maria Janicka

Probabilistic graphical models (PGMs) are widely used to discover latent structure in data, but their success hinges on selecting an appropriate model design. In practice, model specification is difficult and often requires iterative…

Machine Learning · Computer Science 2026-04-08 Kevin Zhang , Yixin Wang

Representation learning in dynamic graphs is a challenging problem because the topology of graph and node features vary at different time. This requires the model to be able to effectively capture both graph topology information and…

Machine Learning · Computer Science 2021-11-16 Xintao Xiang , Tiancheng Huang , Donglin Wang

Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural Networks (GNNs) that incorporate a relational inductive…

Machine Learning · Computer Science 2019-10-24 Fabio Ferreira , Lin Shao , Tamim Asfour , Jeannette Bohg

State-of-the-art differentially private synthetic tabular data has been defined by adaptive 'select-measure-generate' frameworks, exemplified by methods like AIM. These approaches iteratively measure low-order noisy marginals and fit…

Machine Learning · Computer Science 2025-11-14 Samuel Maddock , Shripad Gade , Graham Cormode , Will Bullock

Deep neural networks have been used widely to learn the latent structure of datasets, across modalities such as images, shapes, and audio signals. However, existing models are generally modality-dependent, requiring custom architectures and…

Machine Learning · Computer Science 2021-11-12 Yilun Du , Katherine M. Collins , Joshua B. Tenenbaum , Vincent Sitzmann

An intelligent driving system should dynamically formulate appropriate driving strategies based on the current environment and vehicle status while ensuring system security and reliability. However, methods based on reinforcement learning…

Robotics · Computer Science 2025-09-11 Zuojin Tang , Xiaoyu Chen , Yongqiang Li , Jianyu Chen

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric…

Machine Learning · Computer Science 2018-11-05 Kurtland Chua , Roberto Calandra , Rowan McAllister , Sergey Levine

Recent works in high-dimensional model-predictive control and model-based reinforcement learning with learned dynamics and reward models have resorted to population-based optimization methods, such as the Cross-Entropy Method (CEM), for…

Machine Learning · Computer Science 2020-04-21 Homanga Bharadhwaj , Kevin Xie , Florian Shkurti

It is doubtful that animals have perfect inverse models of their limbs (e.g., what muscle contraction must be applied to every joint to reach a particular location in space). However, in robot control, moving an arm's end-effector to a…

Robotics · Computer Science 2022-09-19 Justus Huebotter , Serge Thill , Marcel van Gerven , Pablo Lanillos

Predictive simulations of complex systems are essential for applications ranging from weather forecasting to drug design. The veracity of these predictions hinges on their capacity to capture the effective system dynamics. Massively…

Computational Physics · Physics 2021-10-20 Pantelis R. Vlachas , Georgios Arampatzis , Caroline Uhler , Petros Koumoutsakos

Adaptive tracking control for rigid body dynamics is of critical importance in control and robotics, particularly for addressing uncertainties or variations in system model parameters. However, most existing adaptive control methods are…

Robotics · Computer Science 2025-02-11 Jiawei Tang , Shilei Li , Ling Shi

Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integration methods and their resolution can be adapted to strike…

Machine Learning · Computer Science 2021-06-21 Tobias Pfaff , Meire Fortunato , Alvaro Sanchez-Gonzalez , Peter W. Battaglia

Efficient skill acquisition, representation, and on-line adaptation to different scenarios has become of fundamental importance for assistive robotic applications. In the past decade, dynamical systems (DS) have arisen as a flexible and…

Robotics · Computer Science 2020-03-27 Matteo Saveriano , Dongheui Lee

We propose a novel approach for learning the evolution that employs differentiable neural networks to approximate the full GENERIC structure. Instead of manually choosing the fitted parameters, we learn the whole model together with the…

Computational Physics · Physics 2021-09-28 Martin Šípka , Michal Pavelka

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…

Machine Learning · Computer Science 2020-06-30 Kimin Lee , Younggyo Seo , Seunghyun Lee , Honglak Lee , Jinwoo Shin

Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control. We develop a method for learning to correspond pairs of dynamical systems via a learned latent…

Machine Learning · Computer Science 2020-06-08 Nam Hee Kim , Zhaoming Xie , Michiel van de Panne

Model-based reinforcement learning algorithms make decisions by building and utilizing a model of the environment. However, none of the existing algorithms attempts to infer the dynamics of any state-action pair from known state-action…

Machine Learning · Computer Science 2020-02-25 Yanchao Sun , Furong Huang