首页 开发技术 其它     /    可靠:强化学习的分布式超参数优化框架-源码

可靠:强化学习的分布式超参数优化框架-源码

上传者: weixin_42099987 | 上传时间:2023/12/18 19:53:57 | 文件大小:39KB | 文件类型:ZIP
可靠:强化学习的分布式超参数优化框架-源码
责任RLiable是用于增强学习代理的快速超参数调整的实验并行化框架。
它旨在满足对可分发的Spark/TF兼容模型的需求,该模型允许以简单reliable方式扩展实验。
执行先决条件:版本Python>=3.6火花3.0.1Hadoop2.7Java1.8Scala2.11注意:scripts/install_spark_hpc.sh提供了Linux(基于Debian)安装脚本。
安装要求创建virtualenv并安装Python依赖项virtualenv-p$(whichpython3)envsourceenv/bin/activatepipinstall-rrequirements.txtpipinstall-rdqn-requirements.txt进行实验当前的优化算法基于配置标志opt

文件下载

资源详情

[{"title":"(29个子文件39KB)可靠:强化学习的分布式超参数优化框架-源码","children":[{"title":"rliable-master","children":[{"title":"nb-requirements.txt <span style='color:#111;'>838B</span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'>1.16KB</span>","children":null,"spread":false},{"title":"utils","children":[{"title":"misc.py <span style='color:#111;'>2.62KB</span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'>3.05KB</span>","children":null,"spread":false},{"title":"template_scheduler.py <span style='color:#111;'>321B</span>","children":null,"spread":false}],"spread":true},{"title":".github","children":[{"title":"workflows","children":[{"title":"linting.yml <span style='color:#111;'>932B</span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"models","children":[{"title":"count_model.py <span style='color:#111;'>1.91KB</span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'>196B</span>","children":null,"spread":false},{"title":"dqn.py <span style='color:#111;'>7.43KB</span>","children":null,"spread":false},{"title":"base_model.py <span style='color:#111;'>427B</span>","children":null,"spread":false}],"spread":true},{"title":"rliable","children":[{"title":"parallel.py <span style='color:#111;'>7.02KB</span>","children":null,"spread":false},{"title":"config","children":[{"title":"optim_dqn.json <span style='color:#111;'>526B</span>","children":null,"spread":false},{"title":"optim_count.json <span style='color:#111;'>281B</span>","children":null,"spread":false}],"spread":true},{"title":"serial.py <span style='color:#111;'>2.01KB</span>","children":null,"spread":false},{"title":"core.py <span style='color:#111;'>1.32KB</span>","children":null,"spread":false}],"spread":true},{"title":"scripts","children":[{"title":"install_spark_hpc.sh <span style='color:#111;'>450B</span>","children":null,"spread":false},{"title":"tf_dqn_train_eval.py <span style='color:#111;'>7.22KB</span>","children":null,"spread":false},{"title":"tf_eval_policy.py <span style='color:#111;'>1.89KB</span>","children":null,"spread":false}],"spread":true},{"title":"optimize.py <span style='color:#111;'>2.41KB</span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'>55B</span>","children":null,"spread":false},{"title":"config","children":[{"title":"config.py <span style='color:#111;'>866B</span>","children":null,"spread":false},{"title":"config_dqn.json <span style='color:#111;'>322B</span>","children":null,"spread":false},{"title":"config_base.json <span style='color:#111;'>204B</span>","children":null,"spread":false},{"title":"config_count.json <span style='color:#111;'>169B</span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'>4.77KB</span>","children":null,"spread":false},{"title":"docs","children":[{"title":"assets","children":[{"title":"rliable-logo.png <span style='color:#111;'>16.21KB</span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"evaluate.py <span style='color:#111;'>1.15KB</span>","children":null,"spread":false},{"title":"dqn-requirements.txt <span style='color:#111;'>95B</span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'>100B</span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【好快吧下载】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【好快吧下载】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【好快吧下载】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,8686821#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明