Taichi Blogs
Training a magic fountain using Taichi's autodiff, an efficient tool for differentiable physical simulation
July 14, 2022 | Mingrui Zhang
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!
We'll never share your information with anyone else and you can opt out at any time.