一个高性能的强化学习环境工具包

Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo
{"title":"一个高性能的强化学习环境工具包","authors":"Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo","doi":"10.1109/CoG51982.2022.9893661","DOIUrl":null,"url":null,"abstract":"This paper addresses the dire need for a platform that efficiently provides a framework for running reinforcement learning (RL) experiments. We propose the CaiRL Environment Toolkit as an efficient, compatible, and more sustainable alternative for training learning agents and propose methods to develop more efficient environment simulations. There is an increasing focus on developing sustainable artificial intelligence. However, little effort has been made to improve the efficiency of running environment simulations. The most popular development toolkit for reinforcement learning, OpenAI Gym, is built using Python, a powerful but slow programming language. We propose a toolkit written in C++ with the same flexibility level but works orders of magnitude faster to make up for Python's inefficiency. This would drastically cut climate emissions. CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research. We demonstrate the effectiveness of CaiRL in the classic control benchmark, comparing the execution speed to OpenAI Gym. Furthermore, we illustrate that CaiRL can act as a drop-in replacement for OpenAI Gym to leverage significantly faster training speeds because of the reduced environment computation time.","PeriodicalId":394281,"journal":{"name":"2022 IEEE Conference on Games (CoG)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CaiRL: A High-Performance Reinforcement Learning Environment Toolkit\",\"authors\":\"Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo\",\"doi\":\"10.1109/CoG51982.2022.9893661\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper addresses the dire need for a platform that efficiently provides a framework for running reinforcement learning (RL) experiments. We propose the CaiRL Environment Toolkit as an efficient, compatible, and more sustainable alternative for training learning agents and propose methods to develop more efficient environment simulations. There is an increasing focus on developing sustainable artificial intelligence. However, little effort has been made to improve the efficiency of running environment simulations. The most popular development toolkit for reinforcement learning, OpenAI Gym, is built using Python, a powerful but slow programming language. We propose a toolkit written in C++ with the same flexibility level but works orders of magnitude faster to make up for Python's inefficiency. This would drastically cut climate emissions. CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research. We demonstrate the effectiveness of CaiRL in the classic control benchmark, comparing the execution speed to OpenAI Gym. Furthermore, we illustrate that CaiRL can act as a drop-in replacement for OpenAI Gym to leverage significantly faster training speeds because of the reduced environment computation time.\",\"PeriodicalId\":394281,\"journal\":{\"name\":\"2022 IEEE Conference on Games (CoG)\",\"volume\":\"21 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE Conference on Games (CoG)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CoG51982.2022.9893661\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Conference on Games (CoG)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CoG51982.2022.9893661","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本文解决了对一个平台的迫切需求,该平台可以有效地为运行强化学习(RL)实验提供框架。我们建议将CaiRL环境工具包作为训练学习代理的有效、兼容和更可持续的替代方案,并提出开发更有效的环境模拟的方法。人们越来越关注可持续发展的人工智能。然而,在提高运行环境模拟的效率方面,人们所做的努力很少。最流行的强化学习开发工具包OpenAI Gym是使用Python构建的,Python是一种功能强大但速度缓慢的编程语言。我们建议用c++编写一个工具包,具有相同的灵活性,但工作速度要快几个数量级,以弥补Python的低效率。这将大大减少气候排放。CaiRL还提供了第一个带有内置JVM和Flash支持的强化学习工具包,用于运行用于强化学习研究的传统Flash游戏。我们在经典控制基准中展示了CaiRL的有效性,并将执行速度与OpenAI Gym进行了比较。此外,我们还说明了由于减少了环境计算时间,CaiRL可以作为OpenAI Gym的直接替代品,从而利用更快的训练速度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
CaiRL: A High-Performance Reinforcement Learning Environment Toolkit
This paper addresses the dire need for a platform that efficiently provides a framework for running reinforcement learning (RL) experiments. We propose the CaiRL Environment Toolkit as an efficient, compatible, and more sustainable alternative for training learning agents and propose methods to develop more efficient environment simulations. There is an increasing focus on developing sustainable artificial intelligence. However, little effort has been made to improve the efficiency of running environment simulations. The most popular development toolkit for reinforcement learning, OpenAI Gym, is built using Python, a powerful but slow programming language. We propose a toolkit written in C++ with the same flexibility level but works orders of magnitude faster to make up for Python's inefficiency. This would drastically cut climate emissions. CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research. We demonstrate the effectiveness of CaiRL in the classic control benchmark, comparing the execution speed to OpenAI Gym. Furthermore, we illustrate that CaiRL can act as a drop-in replacement for OpenAI Gym to leverage significantly faster training speeds because of the reduced environment computation time.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信