ORSuite: Benchmarking Suite for Sequential Operations Models
ORSuite: Benchmarking Suite for Sequential Operations Models
复制标题
ORSuite：顺序操作模型的基准测试套件
DOI：
10.1145/3512798.3512819
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Lee Yu, Christina
中科院分区：
文献类型：
--
作者：
Archer, Christopher;Banerjee, Siddhartha;Cortez, Mayleen;Rucker, Carrie;Sinclair, Sean R.;Solberg, Max;Xie, Qiaomin;Lee Yu, Christina
强化学习（RL）在多个社区受到了广泛关注，但实验主要集中在大规模游戏和机器人任务上。在本文中，我们介绍ORSuite，一个开源的库，包含环境，算法和仪器的操作问题。我们的软件包旨在激励强化学习社区的研究人员开发和评估操作任务的算法，并通过考虑累积奖励之外的指标来考虑这些问题的真正多目标性质。
Reinforcement learning (RL) has received widespread attention across multiple communities, but the experiments have focused primarily on large-scale game playing and robotics tasks. In this paper we introduce ORSuite, an open-source library containing environments, algorithms, and instrumentation for operational problems. Our package is designed to motivate researchers in the reinforcement learning community to develop and evaluate algorithms on operational tasks, and to consider the true multi-objective nature of these problems by considering metrics beyond cumulative reward.