Isaac Gym: A High Performance Learning Platform to Train Policies for Robotics Tasks Directly on GPU

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

Isaac gym is a high performance learning platform to train policies for wide variety of robotics tasks directly on a single graphics card.

Both physics simulation and the neural network policy training reside on gpu and communicate by directly passing data from physics buffers to pytorch tensors without ever going through any cpu bottlenecks.

This leads to blazing fast training times for complex robotics tasks on a single gpu with 1-2 orders of magnitude improvementscompared to conventional rl training that uses a cpu based simulator and gpufor neural networks.

Isaac gym is a high performance learning platform to train policies for wide variety of robotics tasks directly on a single graphics card.

This leads to blazing fast training times for complex robotics tasks on a single graphics card with 1-2 orders of magnitude improvementscompared to conventional rl training that uses a cpu based simulator and gpufor neural networks.

Authors

Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, Gavriel State

◐ Recommended Follows

◐ Latest Activity