stable-envs-v1: Fast and Reproducible Environments with Controllable Variations
Training World Models (WMs) relies on processing large amounts of high-dimensional data, which typically needs to be stored, read into memory, and moved from memory to compute units. In principle, GPU-native rendering avoids this movement of large image tensors from memory to compute cores, allowing for better GPU utilization, and training speed-ups. Rendering on-demand also allows to control perceptual appearance through the application of visual variations on-the-fly, allowing for higher diversity in training. To this end, we introduce stable-envs, an open-source library for fast, GPU-native rendering allowing to apply controllable variations on multiple simulation environments. By rendering image observations directly on GPU, stable-envs allows end-to-end training speed-ups of up to 1.33x, with no loss of performance. Besides faster training runs, stable-envs also enables reproducible, large-scale evaluations through batched physics while maintaining full determinism. stable-envs currently supports 80 simulation environments across multiple CPU- and GPU-backends, and is openly available at: https://github.com/galilai-group/stable-envs
Authors
- Richard Gao (ORCID: https://orcid.org/0000-0001-5916-6433)
- Randall Balestriero (ORCID: https://orcid.org/0000-0002-5692-4187)
- Francesco Capuano
- Ahitagni Das (ORCID: https://orcid.org/0009-0008-2981-5525)
- Sami BuGhanem
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.48550/arxiv.2611.23151
- Primary Topic
- Reinforcement Learning in Robotics
- Type
- preprint