End-to-end differentiable physics for learning and control
© 2018 Curran Associates Inc.All rights reserved. We present a differentiable physics engine that can be integrated as a module in deep neural networks for end-to-end learning. As a result, structured physics knowledge can be embedded into larger systems, allowing them, for example, to match observa...
Main Authors: | Smith, Kevin A, Allen, Kelsey Rebecca, Tenenbaum, Joshua B |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
Format: | Article |
Language: | English |
Published: |
Curran Associates Inc
2020
|
Online Access: | https://hdl.handle.net/1721.1/126615 |
Similar Items
-
Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning
by: Toussaint, Marc A, et al.
Published: (2020) -
OPEn: An Open-ended Physics Environment for Learning Without a Task
by: Gan, Chuang, et al.
Published: (2022) -
End-to-End Optimization of Scene Layout
by: Luo, Andrew, et al.
Published: (2021) -
Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning
by: Allen, Kelsey R, et al.
Published: (2021) -
Toward the end-to-end optimization of particle physics instruments with differentiable programming
by: Dorigo, T, et al.
Published: (2023)