no code implementations • 29 Mar 2024 • Lucas Amoudruz, Sergey Litvinov, Petros Koumoutsakos
Biomedical applications such as targeted drug delivery, microsurgery or sensing rely on reaching precise areas within the body in a minimally invasive way.
no code implementations • 27 Feb 2024 • Han Gao, Sebastian Kaltenbach, Petros Koumoutsakos
We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics.
no code implementations • 1 Feb 2024 • Jan-Philipp von Bassewitz, Sebastian Kaltenbach, Petros Koumoutsakos
However, simulations that capture the full range of spatio-temporal scales in such PDEs are often prohibitively expensive.
no code implementations • 1 Dec 2023 • Rambod Mojgani, Daniel Waelchli, Yifei Guan, Petros Koumoutsakos, Pedram Hassanzadeh
Reinforcement learning is emerging as a potent alternative for developing such closures as it requires only low-order statistics and leads to stable closures.
no code implementations • 11 Sep 2023 • Emmanuel Menier, Sebastian Kaltenbach, Mouadh Yagoubi, Marc Schoenauer, Petros Koumoutsakos
In recent years, techniques based on deep recurrent neural networks have produced promising results for the modeling and simulation of complex spatiotemporal systems and offer large flexibility in model development as they can incorporate experimental and computational data.
no code implementations • 17 May 2023 • Daniel Waelchli, Pascal Weber, Petros Koumoutsakos
In this study, we tackle this challenge by introducing an off-policy inverse multi-agent reinforcement learning algorithm (IMARL).
1 code implementation • 4 Apr 2023 • Ivica Kičić, Pantelis R. Vlachas, Georgios Arampatzis, Michail Chatzimanolakis, Leonidas Guibas, Petros Koumoutsakos
To the best of our knowledge, AdaLED is the first framework that couples a surrogate model with a computational solver to achieve online adaptive learning of effective dynamics.
no code implementations • 3 Mar 2023 • Sebastian Kaltenbach, Phaedon-Stelios Koutsourelakis, Petros Koumoutsakos
To this end, we combine a non-linear autoencoder architecture with a time-continuous model for the latent dynamics in the complex space.
no code implementations • 22 Feb 2023 • Pantelis R. Vlachas, Petros Koumoutsakos
Recurrent Neural Networks (RNNs) have become an integral part of modeling and forecasting frameworks in areas like natural language processing and high-dimensional dynamical systems such as turbulent fluid flows.
no code implementations • 24 Mar 2022 • Pascal Weber, Daniel Wälchli, Mustafa Zeqiri, Petros Koumoutsakos
We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL).
no code implementations • 21 Jun 2021 • H. Jane Bae, Petros Koumoutsakos
We believe that SciMARL creates unprecedented capabilities for the simulation of turbulent flows.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 3 May 2021 • Ioannis Mandralis, Pascal Weber, Guido Novati, Petros Koumoutsakos
The present, data efficient, reinforcement learning algorithm results in an array of patterns that reveal practical flow optimization principles for efficient swimming and the methodology can be transferred to the control of aquatic robotic devices operating under energy constraints.
no code implementations • 21 Feb 2021 • Peter Gunnarson, Ioannis Mandralis, Guido Novati, Petros Koumoutsakos, John O. Dabiri
Efficient point-to-point navigation in the presence of a background flow field is important for robotic applications such as ocean surveying.
no code implementations • 17 Feb 2021 • Pantelis R. Vlachas, Julija Zavadlav, Matej Praprotnik, Petros Koumoutsakos
We believe that the proposed framework provides a dramatic increase to simulation capabilities and opens new horizons for the effective modeling of complex molecular systems.
no code implementations • 24 Aug 2020 • Francesco Varoli, Guido Novati, Pantelis R. Vlachas, Petros Koumoutsakos
We propose Improved Memories Learning (IMeL), a novel algorithm that turns reinforcement learning (RL) into a supervised learning (SL) problem and delimits the role of neural networks (NN) to interpolation.
1 code implementation • 24 Jun 2020 • Pantelis R. Vlachas, Georgios Arampatzis, Caroline Uhler, Petros Koumoutsakos
Here we present a novel systematic framework that bridges large scale simulations and reduced order models to Learn the Effective Dynamics (LED) of diverse complex systems.
1 code implementation • 18 May 2020 • Guido Novati, Hugues Lascombes de Laroussilhe, Petros Koumoutsakos
The modeling of turbulent flows is critical to scientific and engineering problems ranging from aircraft design to weather forecasting and climate prediction.
Multi-agent Reinforcement Learning reinforcement-learning +2
1 code implementation • 9 Oct 2019 • Pantelis R. Vlachas, Jaideep Pathak, Brian R. Hunt, Themistoklis P. Sapsis, Michelle Girvan, Edward Ott, Petros Koumoutsakos
We examine the efficiency of Recurrent Neural Networks in forecasting the spatiotemporal dynamics of high dimensional and reduced order complex systems using Reservoir Computing (RC) and Backpropagation through time (BPTT) for gated network architectures.
no code implementations • 27 May 2019 • Steven Brunton, Bernd Noack, Petros Koumoutsakos
The field of fluid mechanics is rapidly advancing, driven by unprecedented volumes of data from field measurements, experiments and large-scale simulations at multiple spatiotemporal scales.
2 code implementations • ICLR 2019 • Guido Novati, Petros Koumoutsakos
ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency.
1 code implementation • 7 Jul 2018 • Guido Novati, Lakshminarayanan Mahadevan, Petros Koumoutsakos
Controlled gliding is one of the most energetically efficient modes of transportation for natural and human powered fliers.
Robotics
1 code implementation • 2 Jul 2018 • Jana Lipkova, Panagiotis Angelikopoulos, Stephen Wu, Esther Alberts, Benedikt Wiestler, Christian Diehl, Christine Preibisch, Thomas Pyka, Stephanie Combs, Panagiotis Hadjidoukas, Koen van Leemput, Petros Koumoutsakos, John S. Lowengrub, Bjoern Menze
Here we provide a Bayesian machine learning framework for the rational design of improved, personalized radiotherapy plans using mathematical modeling and patient multimodal medical scans.
Computational Engineering, Finance, and Science
1 code implementation • 9 Mar 2018 • Zhong Yi Wan, Pantelis R. Vlachas, Petros Koumoutsakos, Themistoklis P. Sapsis
In this way, the data-driven model improves the imperfect model in regions where data is available, while for locations where data is sparse the imperfect model still provides a baseline for the prediction of the system dynamics.
Chaotic Dynamics Computational Physics
no code implementations • 21 Feb 2018 • Pantelis R. Vlachas, Wonmin Byeon, Zhong Y. Wan, Themistoklis P. Sapsis, Petros Koumoutsakos
We introduce a data-driven forecasting method for high-dimensional chaotic systems using long short-term memory (LSTM) recurrent neural networks.
no code implementations • 7 Feb 2018 • Siddhartha Verma, Guido Novati, Petros Koumoutsakos
Fish in schooling formations navigate complex flow-fields replete with mechanical energy in the vortex wakes of their companions.
no code implementations • ECCV 2018 • Wonmin Byeon, Qin Wang, Rupesh Kumar Srivastava, Petros Koumoutsakos
Video prediction models based on convolutional networks, recurrent networks, and their combinations often result in blurry predictions.