匿名用户2021年11月11日
43阅读
开发技术Python
所属分类人工智能、机器学习/深度学习
授权协议Apache-2.0 License

作品详情

RecSim:AConfigurableRecommenderSystemsSimulationPlatform

RecSimisaconfigurableplatformforauthoringsimulationenvironmentsforrecommendersystems(RSs)thatnaturallysupportssequentialinteractionwithusers.RecSimallowsthecreationofnewenvironmentsthatreflectparticularaspectsofuserbehavioranditemstructureatalevelofabstractionwell-suitedtopushingthelimitsofcurrentreinforcementlearning(RL)andRStechniquesinsequentialinteractiverecommendationproblems.Environmentscanbeeasilyconfiguredthatvaryassumptionsabout:userpreferencesanditemfamiliarity;userlatentstateanditsdynamics;andchoicemodelsandotheruserresponsebehavior.WeoutlinehowRecSimoffersvaluetoRLandRSresearchersandpractitioners,andhowitcanserveasavehicleforacademic-industrialcollaboration.ForadetaileddescriptionoftheRecSimarchitecturepleasereadIeetal.Pleasecitethepaperifyouusethecodefromthisrepositoryinyourwork.

Bibtex@article{ie2019recsim,title={RecSim:AConfigurableSimulationPlatformforRecommenderSystems},author={EugeneIeandChih-weiHsuandMartinMladenovandVihanJainandSanmitNarvekarandJingWangandRuiWuandCraigBoutilier},year={2019},eprint={1909.04847},archivePrefix={arXiv},primaryClass={cs.LG}}

Disclaimer

ThisisnotanofficiallysupportedGoogleproduct.

What'snew12/13/2019:Added(abstract)classesforbothmulti-userenvironmentsandagents.Addedbanditalgorithmsforgeneralizedlinearmodels.InstallationandSampleUsage

ItisrecommendedtoinstallRecSimusing(https://pypi.org/project/recsim/):

pipinstallrecsim

However,thelatestversionofDopamineisnotinPyPIasofDecember,2019.WewanttoinstallthelatestversionfromDopamine'srepositorylikethefollowingbeforeweinstallRecSim.NotethatDopaminerequiresTensorflow1.15.0whichisthefinal1.xreleaseincludingGPUsupportforUbuntuandWindows.

pipinstallgit+https://github.com/google/dopamine.git

Herearesomesamplecommandsyoucouldusefortestingtheinstallation:

gitclonehttps://github.com/google-research/recsimcdrecsim/recsimpythonmain.py--logtostderr\--base_dir="/tmp/recsim/interest_exploration_full_slate_q"\--agent_name=full_slate_q\--environment_name=interest_exploration\--episode_log_file='episode_logs.tfrecord'\--gin_bindings=simulator.runner_lib.Runner.max_steps_per_episode=100\--gin_bindings=simulator.runner_lib.TrainRunner.num_iterations=10\--gin_bindings=simulator.runner_lib.TrainRunner.max_training_steps=100\--gin_bindings=simulator.runner_lib.EvalRunner.max_eval_episodes=5

Youcouldthenstartatensorboardandviewtheoutput

tensorboard--logdir=/tmp/recsim/interest_exploration_full_slate_q/--port=2222

Youcouldalsofindthesimulatedlogsin/tmp/recsim/episode_logs.tfrecord

Tutorials

Togetstarted,pleasecheckoutourColabtutorials.InRecSim:Overview,wegiveabriefoverviewaboutRecSim.Wethentalkabouteachconfigurablecomponent:environmentandrecommenderagent.

Documentation

Pleaserefertothewhitepaperforthehigh-leveldesign.

声明:本文仅代表作者观点,不代表本站立场。如果侵犯到您的合法权益,请联系我们删除侵权资源!如果遇到资源链接失效,请您通过评论或工单的方式通知管理员。未经允许,不得转载,本站所有资源文章禁止商业使用运营!
下载安装【程序员客栈】APP
实时对接需求、及时收发消息、丰富的开放项目需求、随时随地查看项目状态

评论