Abstract:The progression of reinforcement learning algorithms have been driven by challenging benchmarks. The rate in which a researcher can iterate on a problem setting directly impacts the speed of algorithm development. Modern machine learning has produced tools that allow for fast and scalable algorithm development like the JAX library. With the availability of these tools, a serious bottleneck in algorithm development is the availability of large and complex domains for experimentation. Most notably, the JAX reinforcement learning ecosystem does not have any benchmarks that test visual first-person tasks; these domains are crucial for testing both exploration and an agent's ability to overcome partial observability. We introduce JAXenstein: an open-source JAX-based benchmark that implements the Wolfenstein 3D rendering engine for fast and scalable experimentation in visual first-person tasks. JAXenstein is several times faster than comparable vision-based benchmarks, and is easily extensible to more complex first-person domains.
| Comments: | Main paper: 5 pages, supplementary material: 3 pages |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.19926 [cs.LG] |
| (or arXiv:2605.19926v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19926 arXiv-issued DOI via DataCite (pending registration) |
From: Ruo Yu Tao [view email]
[v1]
Tue, 19 May 2026 14:47:55 UTC (610 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。