Isaac Gym: High Performance GPU Based Physics Simulation For Robot LearningDownload PDF

19 Aug 2021, 01:03 (modified: 06 Nov 2021, 23:54)NeurIPS 2021 Datasets and Benchmarks Track (Round 2)Readers: Everyone
Keywords: Simulation, Physics Engine, Reinforcement Learning, Robot Learning
TL;DR: We propose a new GPU based physics simulation for large scale high performance robot learning
Abstract: Isaac Gym offers a high-performance learning platform to train policies for a wide variety of robotics tasks entirely on GPU. Both physics simulation and neural network policy training reside on GPU and communicate by directly passing data from physics buffers to PyTorch tensors without ever going through CPU bottlenecks. This leads to blazing fast training times for complex robotics tasks on a single GPU with 2-3 orders of magnitude improvements compared to conventional RL training that uses a CPU-based simulator and GPUs for neural networks. We host the results and videos at and Isaac Gym can be downloaded at The benchmark and environments are available at
Supplementary Material: zip
7 Replies