JaxARC让抽象推理研究速度提升数千倍，支持大规模强化学习实验。
JaxARC: A High-Performance JAX-based Environment for Abstraction and Reasoning Research
- 基于JAX的无状态函数式设计，实现极致并行计算。
- 相比Gymnasium提速38至5439倍，最高每秒处理7.9亿步。
- 适合需要大规模训练的机器学习研究者，尤其关注推理能力评估者。
抽象与推理语料库（ARC）用于测试人工智能系统从少量示例中进行类人归纳推理的能力。现有基于Gymnasium的强化学习环境因计算瓶颈严重限制了实验规模。本文提出JaxARC，一个开源、高性能的强化学习环境，专为ARC设计，采用JAX实现。其函数式、无状态架构支持大规模并行，相较于匹配批大小的Gymnasium，提速达38至5,439倍，峰值吞吐量达790M steps/second。JaxARC支持多个ARC数据集、灵活的动作空间、可组合的包装器及配置驱动的可复现性，使此前计算上不可行的大规模强化学习研究成为可能。代码已开源：https://github.com/aadimator/JaxARC。
原文摘要 · Abstract (English)
The Abstraction and Reasoning Corpus (ARC) tests AI systems' ability to perform human-like inductive reasoning from a few demonstration pairs. Existing Gymnasium-based RL environments severely limit experimental scale due to computational bottlenecks. We present JaxARC, an open-source, high-performance RL environment for ARC implemented in JAX. Its functional, stateless architecture enables massive parallelism, achieving 38-5,439x speedup over Gymnasium at matched batch sizes, with peak throughput of 790M steps/second. JaxARC supports multiple ARC datasets, flexible action spaces, composable wrappers, and configuration-driven reproducibility, enabling large-scale RL research previously computationally infeasible. JaxARC is available at https://github.com/aadimator/JaxARC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。