期刊
MACHINE LEARNING
卷 110, 期 9, 页码 2419-2468出版社
SPRINGER
DOI: 10.1007/s10994-021-05961-4
关键词
Reinforcement learning; Real-world; Applied reinforcement learning
Reinforcement learning has shown success in artificial domains but faces challenges in practical applications. By identifying and analyzing a series of challenges, as well as presenting existing attempts to tackle them, a path towards addressing these difficulties and making RL more deployable in real-world problems can be paved.
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. In this work, we identify and formalize a series of independent challenges that embody the difficulties that must be addressed for RL to be commonly deployed in real-world systems. For each challenge, we define it formally in the context of a Markov Decision Process, analyze the effects of the challenge on state-of-the-art learning algorithms, and present some existing attempts at tackling it. We believe that an approach that addresses our set of proposed challenges would be readily deployable in a large number of real world problems. Our proposed challenges are implemented in a suite of continuous control environments called realworldrl-suite which we propose an as an open-source benchmark.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据