no code implementations • 22 Jan 2024 • Tatiana Lopez-Guevara, Yulia Rubanova, William F. Whitney, Tobias Pfaff, Kimberly Stachenfeld, Kelsey R. Allen
Accurately simulating real world object dynamics is essential for various applications such as robotics, engineering, graphics, and design.
no code implementations • 8 Dec 2023 • William F. Whitney, Tatiana Lopez-Guevara, Tobias Pfaff, Yulia Rubanova, Thomas Kipf, Kimberly Stachenfeld, Kelsey R. Allen
Realistic simulation is critical for applications ranging from robotics to animation.
no code implementations • 7 Dec 2022 • Kelsey R. Allen, Yulia Rubanova, Tatiana Lopez-Guevara, William Whitney, Alvaro Sanchez-Gonzalez, Peter Battaglia, Tobias Pfaff
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions.
no code implementations • 2 Oct 2022 • Meire Fortunato, Tobias Pfaff, Peter Wirnsberger, Alexander Pritzel, Peter Battaglia
In recent years, there has been a growing interest in using machine learning to overcome the high cost of numerical simulation, with some learned models achieving impressive speed-ups over classical solvers whilst maintaining accuracy.
no code implementations • 1 Feb 2022 • Kelsey R. Allen, Tatiana Lopez-Guevara, Kimberly Stachenfeld, Alvaro Sanchez-Gonzalez, Peter Battaglia, Jessica Hamrick, Tobias Pfaff
In our fluid manipulation tasks, the resulting designs outperformed those found by sampling-based optimization techniques.
no code implementations • ICLR 2022 • Xu Han, Han Gao, Tobias Pfaff, Jian-Xun Wang, Li-Ping Liu
Graph-based next-step prediction models have recently been very successful in modeling complex high-dimensional physical systems on irregular meshes.
1 code implementation • 31 Dec 2021 • Kimberly Stachenfeld, Drummond B. Fielding, Dmitrii Kochkov, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Can Cui, Shirley Ho, Peter Battaglia, Alvaro Sanchez-Gonzalez
We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the comparably low resolutions across various scientifically relevant metrics.
no code implementations • 16 Dec 2021 • Yulia Rubanova, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Peter Battaglia
We can improve the simulation accuracy on a larger system by applying more solver iterations at test time.
no code implementations • 12 Oct 2021 • Dmitrii Kochkov, Tobias Pfaff, Alvaro Sanchez-Gonzalez, Peter Battaglia, Bryan K. Clark
In this work we use graph neural networks to define a structured variational manifold and optimize its parameters to find high quality approximations of the lowest energy solutions on a diverse set of Heisenberg Hamiltonians.
no code implementations • ICLR 2022 • Kim Stachenfeld, Drummond Buschman Fielding, Dmitrii Kochkov, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Can Cui, Shirley Ho, Peter Battaglia, Alvaro Sanchez-Gonzalez
We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the same low resolutions across various scientifically relevant metrics.
11 code implementations • ICLR 2021 • Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez, Peter W. Battaglia
Our model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation.
12 code implementations • ICML 2020 • Alvaro Sanchez-Gonzalez, Jonathan Godwin, Tobias Pfaff, Rex Ying, Jure Leskovec, Peter W. Battaglia
Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another.
no code implementations • ICLR 2020 • Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Theophane Weber, Lars Buesing, Peter W. Battaglia
In SAVE, a learned prior over state-action values is used to guide MCTS, which estimates an improved set of state-action values.
no code implementations • ICLR 2019 • Scott Reed, Yusuf Aytar, Ziyu Wang, Tom Paine, Aäron van den Oord, Tobias Pfaff, Sergio Gomez, Alexander Novikov, David Budden, Oriol Vinyals
The proposed agent can solve a challenging robot manipulation task of block stacking from only video demonstrations and sparse reward, in which the non-imitating agents fail to learn completely.
no code implementations • ICLR 2019 • Tom Le Paine, Sergio Gómez Colmenarejo, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt W. Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas
MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators.
1 code implementation • NeurIPS 2018 • Yusuf Aytar, Tobias Pfaff, David Budden, Tom Le Paine, Ziyu Wang, Nando de Freitas
One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator.