{"ID":2823150,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.01288","arxiv_id":"2601.01288","title":"PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS","abstract":"Reinforcement learning from pixels is often bottlenecked by the performance and complexity of 3D rendered environments. Researchers face a trade-off between high-speed, low-level engines and slower, more accessible Python frameworks. To address this, we introduce PyBatchRender, a Python library for high-throughput, batched 3D rendering that achieves over 1 million FPS on simple scenes. Built on the Panda3D game engine, it utilizes its mature ecosystem while enhancing performance through optimized batched rendering for up to 1000X speedups. Designed as a physics-agnostic renderer for reinforcement learning from pixels, PyBatchRender offers greater flexibility than dedicated libraries, simpler setup than typical game-engine wrappers, and speeds rivaling state-of-the-art C++ engines like Madrona. Users can create custom scenes entirely in Python with tens of lines of code, enabling rapid prototyping for scalable AI training. Open-source and easy to integrate, it serves to democratize high-performance 3D simulation for researchers and developers. The library is available at https://github.com/dolphin-in-a-coma/PyBatchRender.","short_abstract":"Reinforcement learning from pixels is often bottlenecked by the performance and complexity of 3D rendered environments. Researchers face a trade-off between high-speed, low-level engines and slower, more accessible Python frameworks. To address this, we introduce PyBatchRender, a Python library for high-throughput, bat...","url_abs":"https://arxiv.org/abs/2601.01288","url_pdf":"https://arxiv.org/pdf/2601.01288v1","authors":"[\"Evgenii Rudakov\",\"Jonathan Shock\",\"Benjamin Ultan Cowley\"]","published":"2026-01-03T21:19:57Z","proceeding":"cs.GR","tasks":"[\"cs.GR\",\"cs.AI\",\"cs.PF\",\"cs.RO\"]","methods":"[\"Reinforcement Learning\"]","has_code":false,"code_links":[{"ID":605476,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2823150,"paper_url":"https://arxiv.org/abs/2601.01288","paper_title":"PyBatchRender: A Python Library for Batched 3D Rendering at Up to One Million FPS","repo_url":"https://github.com/dolphin-in-a-coma/PyBatchRender","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}