SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Christopher Yeh;Victor Li;Rajeev Datta;Julio Arroyo;Nicolas H. Christianson;Chi Zhang;Yize Chen;Mohammad Mehdi Hosseini;A. Golmohammadi;Yuanyuan Shi;Yisong Yue;Adam Wierman
中科院分区：
文献类型：
--
作者：
Christopher Yeh;Victor Li;Rajeev Datta;Julio Arroyo;Nicolas H. Christianson;Chi Zhang;Yize Chen;Mohammad Mehdi Hosseini;A. Golmohammadi;Yuanyuan Shi;Yisong Yue;Adam Wierman
在可持续发展应用中，由于缺乏强化学习（RL）的标准化基准，因此很难跟踪特定领域的进展，也很难确定研究人员集中精力的瓶颈。在本文中，我们介绍了SustainGym，这是一套五个环境，旨在测试RL算法在现实可持续能源系统任务上的性能，从电动汽车充电到碳感知数据中心作业调度。环境测试RL算法在现实的分布变化，以及在多代理设置。我们表明，标准的现成RL算法为提高性能留下了很大的空间，并强调了将RL引入现实世界的可持续性任务所面临的挑战。
The lack of standardized benchmarks for reinforcement learning (RL) in sustainability applications has made it difficult to both track progress on specific domains and identify bottlenecks for researchers to focus their efforts. In this paper, we present SustainGym, a suite of five environments designed to test the performance of RL algorithms on realistic sustainable energy system tasks, ranging from electric vehicle charging to carbon-aware data center job scheduling. The environments test RL algorithms under realistic distribution shifts as well as in multi-agent settings. We show that standard off-the-shelf RL algorithms leave significant room for improving performance and highlight the challenges ahead for introducing RL to real-world sustainability tasks.