Taichi Blogs
Improving Gradient Computation for Differentiable Physics Simulation with Contacts
Note: If you have any comments or suggestions regarding the content of this article, you can contact the author of the original post.
Training a magic fountain using Taichi's autodiff, an efficient tool for differentiable physical simulation
With the generated gradient information, a differentiable physical simulator can make the convergence of the machine learning process one order of magnitude faster than gradient-free algorithms, such as model-free reinforcement learning.
Subscribe to our updates
Get the latest news from the Taichi Lang community in a monthly email: Groundbreaking releases, upcoming events, new insights, community updates, and more!