arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.08272cs.LGq-bio.QM
收藏

深度强化学习在保护决策中的应用

Deep Reinforcement Learning for Conservation Decisions

University of California, Berkeley(加州大学伯克利分校)

Marcus Lapeyrolerie, Melissa S. Chapman, Kari E. A. Norman, Carl Boettiger

摘要:

机器学习能帮助我们对不断变化的地球做出更好的决策吗?在本文中,我们说明并讨论了机器学习的一个有前途的角落,称为_强化学习_(RL),以帮助解决最具挑战性的保护决策问题的潜力。RL非常适合保护和全球变化挑战,原因有三个:(1)RL明确专注于设计与动态和不确定的环境进行交互的代理,(2)RL方法不需要大量数据,(3)RL方法将利用而不是取代现有的模型、模拟及其包含的知识。我们提供了一个概念和技术介绍RL及其相关的生态和保护的挑战,包括在设定渔业配额和管理生态临界点的问题的例子。四个带有注释代码的附录为希望采用、评估或扩展这些方法的研究人员提供了切实的介绍。

英文摘要:

Can machine learning help us make better decisions about a changing planet? In this paper, we illustrate and discuss the potential of a promising corner of machine learning known as _reinforcement learning_ (RL) to help tackle the most challenging conservation decision problems. RL is uniquely well suited to conservation and global change challenges for three reasons: (1) RL explicitly focuses on designing an agent who _interacts_ with an environment which is dynamic and uncertain, (2) RL approaches do not require massive amounts of data, (3) RL approaches would utilize rather than replace existing models, simulations, and the knowledge they contain. We provide a conceptual and technical introduction to RL and its relevance to ecological and conservation challenges, including examples of a problem in setting fisheries quotas and in managing ecological tipping points. Four appendices with annotated code provide a tangible introduction to researchers looking to adopt, evaluate, or extend these approaches.

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。

↑