Sorry to revive this thread, but I am facing the exact same problem and encountered an additional issue. Any non-zero environment spacing makes environments behave different, even if the environments are supposed to be exactly the same. However, setting it to zero makes the simulation slow. Has anyone encountered this same problem as well?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Error during RL examples | 2 | 881 | October 12, 2022 | |
| Different results based on environment spacing | 3 | 1127 | August 16, 2022 | |
| How to increase the PxgDynamicsMemoryConfig::foundLostAggregatePairsCapacity buffer in python | 2 | 973 | November 2, 2023 | |
| Error PxgCudaDeviceMemoryAllocator fail to allocate memory 2147483648 bytes! Result = 2 | 6 | 2299 | April 25, 2023 | |
| Error due to buffer overflow despite having enough GPU memory when setting large `numEnvs` | 0 | 1011 | February 26, 2023 | |
| Simulation crush while training agent in Isaac Sim | 2 | 759 | October 4, 2023 | |
| Maximize the GPU resources when using repo OmniIsaacGymEnvs | 1 | 690 | September 21, 2023 | |
| Env_spacing zero results in an error | 3 | 382 | February 7, 2023 | |
| Max number of parallel envs in Isaac Sim | 2 | 840 | March 10, 2023 | |
| Max number of rigidbodies? | 12 | 3162 | May 30, 2017 |