A curated list of awesome Intuitive Physics resources. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers, and awesome-architecture-search
Intuitive Physics is about utilizing machine learning techniques to learn physics. These are some of the awesome resources! This topic is also strongly related with Model-based Reinforcement Learning.
Please help contribute this list by adding pull request
Markdown format:
- Paper Name [[pdf]](link) [[code]](link)
- Author 1, Author 2 and Author 3. *Conference/Journal Year*- Fast, Robust Adaptive Control by Learning only
Forward Models. [pdf]
- Andrew W. Moore. NIPS 1991
- Locally Weighted Learning for Control. [pdf]
- Christopher G. Atkeson, Andrew W. Moore, and Stefan Schaal. AI Review 1996
- Interaction Networks for Learning about Objects, Relations and Physics. [pdf] [code]
- Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Rezende, Koray Kavukcuoglu. NIPS 2016
- A Compositional Object-Based Approach to Learning Physical Dynamics. [pdf] [code]
- Michael B. Chang, Tomer Ullman, Antonio Torralba, Joshua B. Tenenbaum. ICLR 2017
- Graph networks as learnable physics engines for inference and control
. [pdf] [code]
- Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia. ICML 2018
- Flexible Neural Representation for Physics Prediction. [pdf] [code]
- Damian Mrowca, Chengxu Zhuang, Elias Wang, Nick Haber, Li Fei-Fei, Joshua B. Tenenbaum, Daniel L. K. Yamins.
- Interpretable Intuitive Physics Model. [pdf] [code]
- Tian Ye, Xiaolong Wang, James Davidson, Abhinav Gupta. ECCV 2018
- Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids. [pdf] [code]
- Yunzhu Li, Jiajun Wu, Russ Tedrake, Joshua B. Tenenbaum, Antonio Torralba. ICLR 2019
- Reasoning About Physical Interactions with Object-Oriented Prediction and Planning. [pdf]
- Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu. ICLR 2019
- Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning. [pdf]
- Michael Lutter, Christian Ritter, Jan Peters. ICLR 2019
- Learning Protein Structure with a Differentiable Simulator. [pdf]
- John Ingraham, Adam Riesselman, Chris Sander, Debora Marks. ICLR 2019
- Differentiable Physics-informed Graph Networks. [pdf]
- Sungyong Seo, Yan Liu. ArXiv
To the extent possible under law, we have waived all copyright and related or neighboring rights to this work.