XLand-MiniGrid：基于JAX的可扩展元强化学习环境
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
AI总结：
本文提出XLand-MiniGrid，一个基于JAX的高可扩展元强化学习网格世界环境，提供百万级任务基准和易用基线，并验证其训练速度与任务挑战性。
摘要：
受XLand的多样性与深度以及MiniGrid的简洁性与极简主义启发，我们提出了XLand-MiniGrid，这是一套用于元强化学习研究的工具和网格世界环境。XLand-MiniGrid使用JAX编写，旨在具备高度可扩展性，并有可能在GPU或TPU加速器上运行，从而在有限资源下实现大规模实验的普及化。除了环境之外，XLand-MiniGrid还提供了预采样的基准，包含数百万个难度各异的独特任务，以及易于使用的基线，使用户能够快速开始训练自适应智能体。此外，我们对扩展性和泛化性进行了初步分析，表明我们的基线在训练期间能够达到每秒数百万步的速度，并验证了所提出的基准具有挑战性。XLand-MiniGrid是开源的，可在https://github.com/dunnolab/xland-minigrid获取。
英文摘要：
Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX, XLand-MiniGrid is designed to be highly scalable and can potentially run on GPU or TPU accelerators, democratizing large-scale experimentation with limited resources. Along with the environments, XLand-MiniGrid provides pre-sampled benchmarks with millions of unique tasks of varying difficulty and easy-to-use baselines that allow users to quickly start training adaptive agents. In addition, we have conducted a preliminary analysis of scaling and generalization, showing that our baselines are capable of reaching millions of steps per second during training and validating that the proposed benchmarks are challenging. XLand-MiniGrid is open-source and available at https://github.com/dunnolab/xland-minigrid.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
