论文标题
可推广代理研究（SEGAR）的沙盒环境
The Sandbox Environment for Generalizable Agent Research (SEGAR)
论文作者
论文摘要
在交互式环境中，对连续决策任务进行概括的研究的广泛挑战是设计明显具有里程碑意义的进展的基准。尽管有明显的进展，但当前的基准测试要么不提供适当的曝光，要么对基本因素提供直观的控制，却不易于实施，可自定义或可扩展，或者在计算上运行昂贵。我们将所有这些事情都构建了可推广的代理研究（SEGAR）的沙盒环境。塞加（Segar）提高了RL中概括研究的易用性和问责制，因为通过指定任务分布可以轻松设计概括目标，这又使研究人员能够衡量概括目标的性质。我们介绍了SEGAR及其对这些目标的贡献，以及证明Segar可以帮助回答的一些类型的研究问题的实验。
A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress. While there has been notable headway, current benchmarks either do not provide suitable exposure nor intuitive control of the underlying factors, are not easy-to-implement, customizable, or extensible, or are computationally expensive to run. We built the Sandbox Environment for Generalizable Agent Research (SEGAR) with all of these things in mind. SEGAR improves the ease and accountability of generalization research in RL, as generalization objectives can be easy designed by specifying task distributions, which in turns allows the researcher to measure the nature of the generalization objective. We present an overview of SEGAR and how it contributes to these goals, as well as experiments that demonstrate a few types of research questions SEGAR can help answer.
