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

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

stable-envs-v1: Fast and Reproducible Environments with Controllable Variations

Richard Gao, Randall Balestriero, Francesco Capuano, Ahitagni Das et al.
arXiv (Cornell University)
Reinforcement Learning in Robotics
preprint

stable-envs-v1: Fast and Reproducible Environments with Controllable Variations

Richard Gao, Randall Balestriero, Francesco Capuano, Ahitagni Das, Sami BuGhanem
preprint en

Abstract

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

arXiv (Cornell University)
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon